review-pr-comments
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the GitHub CLI (
gh). It specifically usesgh pr-review review viewand falls back togh apiorgh pr viewto fetch pull request data. These are standard operations for development-oriented skills. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from pull request comments (ingestion point:
gh pr-reviewoutput). - Ingestion points: Data enters the context through command-line output of GitHub PR comments in
SKILL.md. - Boundary markers: The instructions lack boundary markers or specific warnings to ignore instructions embedded within the comments themselves.
- Capability inventory: The agent is authorized to modify the local codebase and interact with the GitHub API to resolve conversations.
- Sanitization: There is no evidence of content sanitization or validation of the external comments before they are interpreted by the agent.
Audit Metadata