handoff
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted data (the current conversation history) to generate its output.
- Ingestion points: The skill reads the entire "current conversation" to produce a summary (SKILL.md).
- Boundary markers: No specific structural delimiters are defined for the output document, though the content is restricted to a summary and a "suggested skills" section.
- Capability inventory: The skill is authorized to write the resulting document to the OS temporary directory (SKILL.md).
- Sanitization: The skill includes a proactive security instruction to "Redact any sensitive information, such as API keys, passwords, or personally identifiable information," which significantly mitigates the risk of leaking secrets into the handoff file.
Audit Metadata