receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill establishes a protocol for technical evaluation of code review feedback, requiring the agent to verify suggestions against the codebase before implementation. This focus on verification serves as a defensive measure against technically incorrect or harmful external suggestions.
- [COMMAND_EXECUTION]: The skill utilizes legitimate commands, such as
grepfor codebase analysis and the GitHub CLI (gh api) for replying to pull request comments. These operations are consistent with the skill's stated purpose of managing development workflows. - [PROMPT_INJECTION]: The instructions include behavioral constraints (e.g., forbidding performative gratitude like "You're absolutely right!") aimed at maintaining technical objectivity. These are standard persona-shaping instructions and do not attempt to bypass safety filters.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data in the form of code review feedback. It mitigates the risk of indirect injection by requiring the agent to cross-reference feedback with the existing codebase and logic before taking any action.
Audit Metadata