handoff
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or configuration.
- [DATA_EXFILTRATION]: While the skill involves reading project files and outputting information, it enforces a strict data safety policy. It explicitly instructs the agent to redact all secrets (API keys, tokens, passwords) and PII, only referencing their locations (e.g., '.env' files) without exposing their values.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files like
CLAUDE.mdorAGENTS.md. It mitigates potential injection risks by instructing the receiving agent to treat the handoff content as unverified context that must be cross-referenced with the codebase before taking action. - [PERSISTENCE]: The skill saves state to a local file (
HANDOFF.mdor a temporary file). This is the intended primary purpose of the skill and does not involve malicious persistence mechanisms like modifying shell profiles or system services.
Audit Metadata