receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, exfiltration attempts, or unauthorized access patterns were detected. The skill is designed to improve technical rigor during the code review process.
- [COMMAND_EXECUTION]: The skill instructs the agent to use
grepto verify the usage of specific code segments before implementing changes ("grep codebase for actual usage"). This is a standard and benign use of development tools for code analysis. - [PROMPT_INJECTION]: The instructions contain guidelines on forbidden responses (e.g., avoiding "You're absolutely right!"). These are persona-based constraints aimed at maintaining technical objectivity rather than attempts to bypass system safety filters.
- [SAFE]: While the skill involves processing external data (code review feedback), it explicitly includes mitigation steps by instructing the agent to "Verify before implementing" and to be skeptical of external reviewers, effectively reducing the risk of indirect prompt injection.
Audit Metadata