receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process and implement feedback from external reviewers, creating an attack surface for indirect prompt injection.
- Ingestion points: External code review feedback.
- Boundary markers: The skill lacks explicit instructions for using delimiters (e.g., XML tags or markdown blocks) to isolate untrusted feedback when processed by the agent.
- Capability inventory: The skill utilizes
grepfor codebase searching and the GitHub CLI (gh api) for replying to comments (SKILL.md). - Sanitization: No programmatic sanitization or validation of the feedback content is specified; the skill relies on the agent's logical evaluation and technical verification steps to mitigate risks.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for verification and interaction.
- Evidence: Use of
grepfor searching the codebase to verify usage (YAGNI check) andgh apifor interacting with the GitHub Pull Request API (SKILL.md).
Audit Metadata