comet-github-pr-review

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from GitHub Pull Requests, creating a surface for indirect prompt injection.
  • Ingestion points: Pull Request body, comments, diffs, and commits accessed via the environment as described in SKILL.md.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' commands to isolate external PR content from the agent's instructions.
  • Capability inventory: The skill generates Markdown comments intended for user review and references a separate 'comet-github-issue-fix' workflow for potential modifications.
  • Sanitization: None identified; the skill is instructed to evaluate the logic of the external content without explicit filtering or escaping of potential instruction-like patterns in the text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:00 PM
Security Audit — agent-trust-hub — comet-github-pr-review