handoff
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could lead to context poisoning or indirect instruction injection.
- Ingestion points: The skill ingests data from the current active conversation and results from the
/context-recalltool as described in the 'Process' and 'Instructions' sections. - Boundary markers: The generated markdown template in the 'Generate Handoff Document' section lacks explicit delimiters or instructions for the receiving agent to ignore potentially malicious content within the interpolated fields (e.g., Task, Rationale, Stakeholder Input).
- Capability inventory: The skill possesses file-system write capabilities, specifically writing the aggregated context to
context/handoffs/current-session.md. - Sanitization: No evidence of sanitization, validation, or escaping of the extracted session content is present before it is written to the handoff file.
Audit Metadata