handoff
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill compacts conversation history and user-provided arguments into a summary, which creates a surface for indirect prompt injection if the conversation contains adversarial instructions.
- Ingestion points: Conversation history and user arguments as defined in
SKILL.md. - Boundary markers: The skill does not define specific delimiters to isolate the summarized content.
- Capability inventory: File writing access to the operating system's temporary directory.
- Sanitization: The skill contains explicit instructions to redact sensitive data (API keys, passwords, PII) before outputting the document.
Audit Metadata