handoff
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted conversation history to generate a handoff document, which represents a potential injection surface.
- Ingestion points: The entire conversation history is ingested to create the summary (SKILL.md).
- Boundary markers: No specific delimiters are specified to isolate untrusted input within the prompt.
- Capability inventory: The skill utilizes file system access to write the summary to a temporary directory (SKILL.md).
- Sanitization: The instructions include a specific directive to redact sensitive information like API keys, passwords, and PII before saving the document.
- [DATA_EXPOSURE]: The skill instructs the agent to save the generated handoff document to the user's OS temporary directory instead of the current workspace. While this is standard for temporary data, users should note that the content is stored outside the primary project environment.
Audit Metadata