write-handoff
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes conversation history to generate a handoff document, which acts as a bridge to a successor agent. This creates a potential surface where malicious instructions in the current session could be carried over to the next.
- Ingestion points: The entire conversation history (SKILL.md).
- Boundary markers: None explicitly mentioned for the summary content itself.
- Capability inventory: File system writes to temporary directories and platform-mediated background agent launching.
- Sanitization: The skill includes explicit instructions to redact secrets, API keys, and personal data, which mitigates the risk of credential exfiltration.
- [SAFE]: The skill demonstrates security-conscious design by enforcing the redaction of sensitive information and restricting file writes to OS-managed temporary locations rather than the project workspace.
Audit Metadata