receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the GitHub CLI (
gh) to reply to pull request comments. - Evidence:
gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/repliesinSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes code review feedback from external reviewers, which represents an attack surface for instructions embedded in data.
- Ingestion points: Code review feedback from external parties (GitHub PR reviewers).
- Boundary markers: The skill does not define specific delimiters for separating feedback content from the agent's internal instructions.
- Capability inventory: The agent is granted capabilities to modify the codebase and interact with the GitHub API via CLI tools.
- Sanitization: No explicit sanitization or filtering of external feedback is described, although the skill mandates technical verification of all suggestions before implementation.
Audit Metadata