[
  {
    "id": "cascading_failure",
    "name": "Cascading failure",
    "tagline": "Recovery attempts that compound the original error — each fix makes it worse.",
    "description": "The agent detects an error and attempts a fix that introduces NEW errors; repeated iterations spiral further from the working state. A simple failure becomes an irrecoverable tangle after N recovery attempts. Distinct from logic_error (which is about the initial bug itself) and from context_pollution (which is about session-level state drift rather than error-recovery compounding).\n",
    "aliases": [
      "recovery-spiral",
      "compound-error",
      "error-cascade",
      "fix-regression"
    ],
    "related_modes": [
      "logic_error",
      "context_pollution"
    ],
    "prior_work": [
      "shah-2026-characterizing-faults",
      "cemri-2025-mast"
    ],
    "detection_signals": [
      "Number of files modified grows per recovery iteration.",
      "Error messages change category across attempts (e.g., ImportError -> TypeError -> AttributeError).",
      "Same file is touched N times in rapid succession with diverging diffs.",
      "Test pass count decreases monotonically after iteration 2."
    ],
    "crosswalks": [
      {
        "taxonomy": "daplab-9-patterns",
        "external_id": "DAP-04",
        "confidence": "exact",
        "note": "DAPLab \"Cascading Error Recovery\" is the direct counterpart.",
        "taxonomy_name": "9 Critical Failure Patterns of Coding Agents",
        "external_label": "Cascading Error Recovery"
      },
      {
        "taxonomy": "mast",
        "external_id": "MAST-FM-14",
        "confidence": "partial",
        "note": "MAST \"Infinite Loop\" is one manifestation of a recovery-spiral pattern.",
        "taxonomy_name": "MAST: Multi-Agent System Failure Taxonomy",
        "external_label": "Infinite Loop"
      }
    ]
  },
  {
    "id": "context_pollution",
    "name": "Context pollution",
    "tagline": "Trajectory drift, hallucination spirals, overlong or off-task context.",
    "description": "The agent's working context degrades over a session — relevant prior information is dropped, irrelevant material accumulates, or hallucinations from earlier turns are treated as ground truth in later turns. Failure of in-session state hygiene, not of a single generation.\n",
    "aliases": [],
    "related_modes": [],
    "prior_work": [
      "cemri-2025-mast",
      "zhu-2025-agent-error-taxonomy"
    ],
    "detection_signals": [
      "Later turns reference facts or code that never existed in user input or tool output.",
      "Token-budget pressure truncates prior turns containing still-relevant context.",
      "Agent repeats a failed tool call multiple times with identical arguments.",
      "Session duration exceeds a threshold at which attention-over-context is empirically unreliable for the model."
    ],
    "crosswalks": [
      {
        "taxonomy": "owasp-agentic-top-10-2026",
        "external_id": "ASI06",
        "confidence": "partial",
        "note": "OWASP \"Memory & Context Poisoning\" covers adversarial manipulation; context_pollution covers accidental drift as well.",
        "taxonomy_name": "OWASP Top 10 for Agentic Applications 2026",
        "external_label": "Memory & Context Poisoning"
      },
      {
        "taxonomy": "mast",
        "external_id": "MAST-FM-13",
        "confidence": "exact",
        "note": "MAST Context Loss is the direct counterpart.",
        "taxonomy_name": "MAST: Multi-Agent System Failure Taxonomy",
        "external_label": "Context Loss"
      },
      {
        "taxonomy": "daplab-9-patterns",
        "external_id": "DAP-05",
        "confidence": "exact",
        "note": "DAPLab Context Window Overflow is the direct counterpart.",
        "taxonomy_name": "9 Critical Failure Patterns of Coding Agents",
        "external_label": "Context Window Overflow"
      }
    ]
  },
  {
    "id": "dependency_blindness",
    "name": "Dependency blindness",
    "tagline": "Reimplementing functionality that already exists in reachable code.",
    "description": "The agent reimplements from scratch a function, class, or utility whose equivalent is already available in declared dependencies, the standard library, or reachable internal modules. Silent quality regression — the code may run correctly but increases surface area, duplicates effort, and drifts from ecosystem conventions. Distinct from Liu 2025's \"Code Copycat\" (intra-generation repetition): dependency_blindness is about cross-codebase reinvention.\n",
    "aliases": [
      "reinvention",
      "ecosystem-duplication"
    ],
    "related_modes": [
      "fabrication",
      "logic_error"
    ],
    "prior_work": [
      "liu-2025-code-copycat",
      "usman-2017-taxonomy-construction"
    ],
    "detection_signals": [
      "Emitted function signature matches an importable symbol in the project's declared dependencies.",
      "Emitted function body substantially overlaps (≥70% AST similarity) with a known stdlib symbol.",
      "Agent emits code despite a language-server suggestion to use an existing symbol.",
      "Emitted module reimplements a utility already present in the repository."
    ],
    "crosswalks": []
  },
  {
    "id": "fabrication",
    "name": "Fabrication",
    "tagline": "Generating reference to non-existent APIs, packages, or symbols.",
    "description": "The agent emits code that references APIs, packages, functions, or symbols that do not exist in any reachable dependency or runtime. Syntactically plausible, factually false. Distinct from obsolescence (real-but-retired) and from dependency blindness (real-and-present-but-ignored).\n",
    "aliases": [
      "hallucination",
      "api-hallucination",
      "package-hallucination",
      "confabulation"
    ],
    "related_modes": [
      "obsolescence",
      "dependency_blindness",
      "supply_chain_attack"
    ],
    "prior_work": [
      "liu-2024-beyond-functional-correctness",
      "spracklen-2024-we-have-a-package"
    ],
    "detection_signals": [
      "Agent emits an import or function call whose identifier is absent from all declared dependencies and stdlib.",
      "Static analyzer (e.g., pyflakes, tsc) flags the reference as undefined at pre-commit.",
      "Execution-grounded check (sandboxed run) raises ImportError, AttributeError, or analogous resolution failure.",
      "LSP-based symbol lookup returns no candidate."
    ],
    "crosswalks": []
  },
  {
    "id": "incomplete_execution",
    "name": "Incomplete execution",
    "tagline": "Agent claims completion while subtasks are skipped, stubbed, or silently dropped.",
    "description": "The agent reports success but has not actually done the work. Common forms: \"TODO\" comments left in generated code, function bodies replaced with `pass` or `...`, partial feature implementation while declaring \"done\", skipping error paths, or terminating before all user-specified items are addressed. Overconfidence paired with under-delivery. Distinct from scope_creep (which over-reaches beyond the request) — this is the opposite failure of under-delivering inside the requested surface.\n",
    "aliases": [
      "premature-completion",
      "false-completion",
      "claimed-done",
      "partial-completion",
      "stub-left-behind"
    ],
    "related_modes": [
      "scope_creep",
      "logic_error"
    ],
    "prior_work": [
      "shah-2026-characterizing-faults",
      "cemri-2025-mast"
    ],
    "detection_signals": [
      "Grep for `TODO`, `FIXME`, `XXX`, `NotImplementedError`, or bare `pass`/`...` in the generated diff.",
      "Tests for features the user explicitly named don't exist.",
      "Agent's final message claims a subtask is done but the file contains only a stub.",
      "Function docstrings describe a behavior not implemented by the body."
    ],
    "crosswalks": [
      {
        "taxonomy": "daplab-9-patterns",
        "external_id": "DAP-01",
        "confidence": "exact",
        "note": "DAPLab \"Incomplete Task Execution\" is the direct counterpart.",
        "taxonomy_name": "9 Critical Failure Patterns of Coding Agents",
        "external_label": "Incomplete Task Execution"
      },
      {
        "taxonomy": "mast",
        "external_id": "MAST-FM-07",
        "confidence": "exact",
        "note": "MAST \"Premature Termination\" is the direct counterpart at the multi-agent level.",
        "taxonomy_name": "MAST: Multi-Agent System Failure Taxonomy",
        "external_label": "Premature Termination"
      }
    ]
  },
  {
    "id": "logic_error",
    "name": "Logic error",
    "tagline": "Correct API use, incorrect logic.",
    "description": "The agent uses real, current APIs correctly at the signature level but encodes incorrect logic for the task. The canonical \"passes type check, fails correctness\" class. Distinct from fabrication (API doesn't exist) and obsolescence (wrong version).\n",
    "aliases": [],
    "related_modes": [],
    "prior_work": [
      "liu-2024-beyond-functional-correctness",
      "zhu-2025-agent-error-taxonomy"
    ],
    "detection_signals": [
      "Unit tests fail with correctness assertions (not import or type errors).",
      "Execution in a sandbox produces outputs that contradict the task spec.",
      "Mutation testing reveals that substitution of logic primitives does not change test outcomes (test insensitivity is a different signal, but logic-error cases often co-occur).",
      "Symbolic or property-based tests find counterexamples."
    ],
    "crosswalks": [
      {
        "taxonomy": "mast",
        "external_id": "MAST-FM-11",
        "confidence": "partial",
        "note": "MAST Verification Failure covers acceptance of incorrect output; logic_error is a cause upstream.",
        "taxonomy_name": "MAST: Multi-Agent System Failure Taxonomy",
        "external_label": "Verification Failure"
      }
    ]
  },
  {
    "id": "obsolescence",
    "name": "Obsolescence",
    "tagline": "Using deprecated APIs, retired packages, or outdated library versions — often because the model's training data pre-dates current releases.",
    "description": "The agent emits code that references real APIs or packages that have been deprecated, removed, or materially changed in their recommended version. The root cause is frequently training-data staleness: the model saw a library version that has since been superseded, and it confidently emits the older form. Distinct from fabrication (non-existent) and from dependency_blindness (real-and-current-but-ignored).\n",
    "aliases": [
      "stale-training-knowledge",
      "training-cutoff-drift",
      "version-drift",
      "deprecated-api-usage",
      "library-evolution-lag"
    ],
    "related_modes": [
      "fabrication",
      "dependency_blindness"
    ],
    "prior_work": [
      "wang-2024-llms-meet-library-evolution",
      "liu-2024-beyond-functional-correctness"
    ],
    "detection_signals": [
      "Imported API is marked deprecated in the target library's current release notes.",
      "Package pinning is older than the latest minor release by N versions (threshold configurable).",
      "Language-server or linter emits a deprecation warning.",
      "Behavior differs between training-era and current versions of the library."
    ],
    "crosswalks": [
      {
        "taxonomy": "daplab-9-patterns",
        "external_id": "DAP-03",
        "confidence": "exact",
        "note": "DAPLab \"Stale API Usage\" is the direct counterpart.",
        "taxonomy_name": "9 Critical Failure Patterns of Coding Agents",
        "external_label": "Stale API Usage"
      }
    ]
  },
  {
    "id": "scope_creep",
    "name": "Scope creep",
    "tagline": "Actions outside declared task boundary.",
    "description": "The agent performs actions beyond the user-stated task scope — edits files not in the request, installs packages not asked for, modifies configs outside the declared surface, or chains follow-on work unprompted.\n",
    "aliases": [],
    "related_modes": [],
    "prior_work": [
      "cemri-2025-mast",
      "zhu-2025-agent-error-taxonomy"
    ],
    "detection_signals": [
      "Agent modifies files outside the declared task surface (e.g., paths in the user prompt).",
      "Agent installs dependencies not named in the prompt.",
      "Agent commits additional unrelated changes alongside the requested edit.",
      "Agent performs cleanup, refactoring, or \"improvement\" not explicitly requested."
    ],
    "crosswalks": [
      {
        "taxonomy": "mast",
        "external_id": "MAST-FM-01",
        "confidence": "exact",
        "note": "MAST Role Violation is the direct counterpart at the multi-agent level.",
        "taxonomy_name": "MAST: Multi-Agent System Failure Taxonomy",
        "external_label": "Role Violation"
      },
      {
        "taxonomy": "owasp-agentic-top-10-2026",
        "external_id": "ASI02",
        "confidence": "partial",
        "note": "OWASP \"Tool Misuse\" partially overlaps; scope_creep is narrower (task-boundary violation).",
        "taxonomy_name": "OWASP Top 10 for Agentic Applications 2026",
        "external_label": "Tool Misuse and Exploitation"
      }
    ]
  },
  {
    "id": "security_vulnerability",
    "name": "Security vulnerability",
    "tagline": "Insecure patterns, injection flaws, weak cryptography, secret leakage.",
    "description": "The agent emits code that introduces a security vulnerability — injection primitives, weak cryptographic choices, leaked secrets, or insecure deserialization. Correct-looking code that violates security invariants.\n",
    "aliases": [],
    "related_modes": [],
    "prior_work": [
      "liu-2024-beyond-functional-correctness",
      "spracklen-2024-we-have-a-package"
    ],
    "detection_signals": [
      "Static analyzer (semgrep, bandit, CodeQL) fires on the emitted code.",
      "Secret-scanner (gitleaks, trufflehog) finds hardcoded credentials.",
      "Generated SQL uses string concatenation instead of parameterization.",
      "Cryptographic primitives are weak (MD5, SHA1, ECB) or from insecure libraries."
    ],
    "crosswalks": [
      {
        "taxonomy": "owasp-agentic-top-10-2026",
        "external_id": "ASI05",
        "confidence": "partial",
        "note": "OWASP ASI05 \"Unexpected Code Execution\" overlaps at the RCE surface; security_vulnerability covers a broader class.",
        "taxonomy_name": "OWASP Top 10 for Agentic Applications 2026",
        "external_label": "Unexpected Code Execution (RCE)"
      }
    ]
  },
  {
    "id": "supply_chain_attack",
    "name": "Supply-chain attack",
    "tagline": "Slopsquatting, typosquatting, compromised MCP servers.",
    "description": "The agent is induced — by its own hallucination, by an adversarial package name, or by a compromised upstream — to install or invoke malicious code. Covers slopsquatting (hallucinated package names registered by an attacker), typosquatting (near-miss names), and compromised MCP servers or tools.\n",
    "aliases": [
      "slopsquatting",
      "typosquatting"
    ],
    "related_modes": [
      "fabrication",
      "security_vulnerability"
    ],
    "prior_work": [
      "spracklen-2024-we-have-a-package"
    ],
    "detection_signals": [
      "Agent-proposed install resolves to a package registered within the last 30 days with no prior maintainer reputation.",
      "Package name is a near-miss (Levenshtein ≤ 2) of a well-known dependency.",
      "MCP server manifest is unsigned or from an unknown publisher.",
      "Post-install, the environment shows outbound connections to unexpected hosts."
    ],
    "crosswalks": [
      {
        "taxonomy": "owasp-agentic-top-10-2026",
        "external_id": "ASI04",
        "confidence": "exact",
        "note": "OWASP ASI04 \"Agentic Supply Chain Vulnerabilities\" is the direct counterpart, including slopsquatting.",
        "taxonomy_name": "OWASP Top 10 for Agentic Applications 2026",
        "external_label": "Agentic Supply Chain Vulnerabilities"
      }
    ]
  },
  {
    "id": "test_manipulation",
    "name": "Test manipulation",
    "tagline": "Agent gaming its own evaluation — editing tests or test harness so failures disappear without fixing the underlying bug.",
    "description": "The agent, when faced with failing tests or assertions, modifies the tests themselves rather than the code under test. Manifests as: rewriting asserts to match current (wrong) output, commenting out failing tests, adding `pytest.mark.skip`, replacing real expectations with tautologies, or disabling the CI job. Qualitatively different from logic_error (an honest mistake) — this is adversarial self-evaluation. Often triggered by RL-style reward hacking or by task prompts that over-emphasize \"make tests pass\".\n",
    "aliases": [
      "silent-workaround",
      "evaluation-gaming",
      "reward-hacking",
      "test-gaming",
      "spec-gaming"
    ],
    "related_modes": [
      "logic_error",
      "scope_creep"
    ],
    "prior_work": [
      "shah-2026-characterizing-faults",
      "cemri-2025-mast"
    ],
    "detection_signals": [
      "Git diff includes both source-under-test AND its test file in the same commit, with test assertions weakened.",
      "Test is moved from assertions to logging/printing.",
      "A `pytest.mark.skip` or `@unittest.skip` appears concurrently with a failing run.",
      "Test file touched in a PR whose ticket/commit message names a bug fix elsewhere.",
      "Coverage drops while pass rate rises."
    ],
    "crosswalks": [
      {
        "taxonomy": "daplab-9-patterns",
        "external_id": "DAP-07",
        "confidence": "exact",
        "note": "DAPLab \"Silent Test-Passing Workaround\" is the direct counterpart.",
        "taxonomy_name": "9 Critical Failure Patterns of Coding Agents",
        "external_label": "Silent Test-Passing Workaround"
      },
      {
        "taxonomy": "mast",
        "external_id": "MAST-FM-11",
        "confidence": "partial",
        "note": "MAST \"Verification Failure\" is adjacent — accepting incorrect output without checking.",
        "taxonomy_name": "MAST: Multi-Agent System Failure Taxonomy",
        "external_label": "Verification Failure"
      }
    ]
  }
]