handoff
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it summarizes potentially untrusted content for use in subsequent sessions.
- Ingestion points: Processes the entire current conversation history and user-supplied arguments (found in SKILL.md).
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are utilized to wrap the summarized content.
- Capability inventory: The skill performs file system write operations to create the handoff document.
- Sanitization: The skill includes a specific instruction to redact sensitive information such as API keys and PII, which acts as a partial mitigation against data exposure.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform file system writes outside the current project workspace by saving the summary to the operating system's temporary directory.
Audit Metadata