handoff
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface (Category 8).
- Ingestion points: Processes the entire current conversation history and user-supplied arguments from SKILL.md to generate the handoff document.
- Boundary markers: The skill does not provide instructions to wrap the summarized content in delimiters or warnings for the next agent, which could lead the receiving agent to treat the summary as authoritative instructions.
- Capability inventory: The agent is instructed to write files to the OS temporary directory based on this summarized content.
- Sanitization: While the skill correctly instructs the agent to redact credentials (API keys, passwords), it lacks validation or escaping mechanisms to prevent executable instructions within the conversation from being interpreted as commands by the next agent.
- [COMMAND_EXECUTION]: The skill directs the agent to perform file system operations outside the designated workspace by saving the handoff document to the operating system's temporary directory (`Save to the temporary directory of the user's OS
- not the current workspace`).
Audit Metadata