receiving-code-review
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill defines strict rules for the agent's conversational style, specifically forbidding polite or performative phrases (e.g., "Thank you", "You're right"). While this overrides default AI behavior patterns, it is a functional stylistic choice intended to improve technical accuracy and prevent "hallucinatory agreement" during code reviews.
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard CLI tools such as
grepfor codebase analysis and the GitHub CLI (gh api) for replying to pull request comments. These tools are used within their intended scope for developer workflows. - [DATA_EXFILTRATION]: No evidence of unauthorized data access or external transmission was found. The use of the GitHub API is constrained to pull request interactions within the user's repository context.
Audit Metadata