handoff
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill generates a summary of the current conversation history to be used by a subsequent agent session. This creates a surface where malicious instructions embedded in the processed conversation could be carried over and potentially influence the behavior of the fresh agent.\n
- Ingestion points: Processes the entire current conversation history (SKILL.md).\n
- Boundary markers: No explicit delimiters or boundary markers are defined to isolate the summarized content from instructions in the handoff document.\n
- Capability inventory: The skill instructs the agent to write files to the operating system's temporary directory.\n
- Sanitization: The instructions explicitly mandate the redaction of sensitive information such as API keys, passwords, and PII, which serves as a security control.\n- [COMMAND_EXECUTION]: The skill directs the agent to save documents to the user's OS temporary directory, requiring file system operations through the agent's available tools.
Audit Metadata