github-code-review

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process and analyze untrusted external data from GitHub pull requests, creating a surface for indirect prompt injection attacks.
  • Ingestion points: The skill reads PR metadata, file diffs, and issue text as described in the 'Review Order' and 'Evidence Sources' sections of SKILL.md.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or provide warnings to the agent to ignore potentially malicious instructions embedded in code comments or diffs.
  • Capability inventory: The agent uses gh and git CLI tools to retrieve data. While these tools are used for reading, the resulting output is processed directly by the model.
  • Sanitization: Absent. No filtering, escaping, or validation logic is defined for the external data ingested during the review process.
  • [COMMAND_EXECUTION]: The skill utilizes local CLI tools including gh pr view, gh pr diff, and git diff to fetch repository information. This is standard behavior for a code review tool and aligns with its primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 05:23 PM
Security Audit — agent-trust-hub — github-code-review