github-code-review

Warn

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: MEDIUMCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill attempts to retrieve the GITHUB_TOKEN from sensitive locations, including the user's ~/.git-credentials file and local environment files (.env). While functional for GitHub API interaction, these files contain sensitive authentication data.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external GitHub Pull Requests, creating a vulnerability surface where malicious content in a PR could influence agent behavior.
  • Ingestion points: Retrieves PR metadata (title, body) and file contents through the GitHub REST API and git fetch operations (SKILL.md).
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the reviewed PR content.
  • Capability inventory: The skill uses powerful tools including git, gh, curl, and suggests running local test suites like pytest or npm test on the checked-out PR code (SKILL.md).
  • Sanitization: No input validation or sanitization of PR content is performed before it is processed by the agent.
  • [COMMAND_EXECUTION]: Utilizes shell scripts to parse system files and manage repository workflows, including checking out external PR branches.
  • [EXTERNAL_DOWNLOADS]: Downloads PR metadata and repository content from GitHub's official infrastructure to facilitate the review process.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 28, 2026, 12:48 PM
Security Audit — agent-trust-hub — github-code-review