Skip to main content
SAICA-KG

Incidents

GitHub Copilot induced to disclose real hard-coded secrets via redaction prompts

CUHK researchers showed Copilot can reconstruct real secrets from redacted public GitHub code; 6.4% of sampled Copilot-active repos leaked live credentials completable via masked prompts.

2024-05-01security breachconfirmed

Description

Researchers at the Chinese University of Hong Kong demonstrated that GitHub Copilot could be induced to reproduce verbatim hard-coded credentials (API keys, tokens, passwords) present in its training data by prompting it to complete redacted portions of public source files. In a sample of ~20,000 repositories where Copilot was active, over 1,200 (6.4%) leaked at least one secret via this technique — a 40% higher incidence than the base rate of public-repo secret leakage. The finding confirmed that LLM code-completion tools can act as a secondary exfiltration channel for credentials independent of any live-system compromise.

Exhibited failure modes

Affected systems

  • GitHub Copilot

Mitigated by

  • Semgrep — Fast, rule-based static analysis with a pattern syntax that mirrors source code.
  • Snyk — Vulnerability scanning for code, dependencies, containers, and IaC.

Sources

Notes

Date approximate (month of public write-up). Mitigations cite tools whose rules catch committed credentials pre-merge — not tools that prevent the model from emitting a secret at completion time. The latter is a training-data problem the KG does not yet model.

View raw YAML on GitHub →