handoff
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill summarizes conversation history that may contain untrusted data from external sources. Malicious instructions within the conversation could potentially be carried over into the handoff document, influencing future agent sessions.\n
- Ingestion points: The skill processes the active conversation context to generate the handoff document.\n
- Boundary markers: No explicit markers or delimiters are defined to isolate untrusted session data from the summarization logic.\n
- Capability inventory: The skill utilizes file-writing capabilities to save documents to the operating system's temporary directory (%TEMP%, $TMPDIR, /tmp).\n
- Sanitization: The instructions include a mandatory rule to redact secrets, tokens, passwords, and PII before writing the file to disk.
Audit Metadata