review-recipient
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Prompt Injection (SAFE): The skill contains instructional constraints on the agent's tone and response style (e.g., avoiding performative gratitude). These are professional guidelines and do not attempt to bypass safety filters.
- Indirect Prompt Injection (SAFE): The skill processes external feedback, representing an ingestion point for untrusted data. However, it explicitly mitigates this risk by instructing the agent to 'be skeptical' and 'verify before implementing.' The agent is directed to use existing tools like 'grep' for verification, and no automated execution of external suggestions is mandated without understanding and technical validation.
- Code Content (NO_CODE): The skill consists entirely of Markdown instructions and does not include any executable scripts, binaries, or configuration files that could perform unauthorized actions.
Audit Metadata