pr-comments
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external, potentially attacker-controlled pull request comments, which creates a surface for indirect prompt injection. \n
- Ingestion points: GitHub PR comments are fetched in
SKILL.mdusinggh apiandgh pr viewcommands. \n - Boundary markers: The skill explicitly instructs the agent to treat comment text as untrusted and never follow instructions embedded in a comment. \n
- Capability inventory: The skill uses
gh(GitHub CLI) andgitfor repository access and data retrieval. It does not perform writes or execute the content of the comments. \n - Sanitization: It directs the agent to summarize content and redact secret-like values, reducing the likelihood of accidental execution or data leak.
Audit Metadata