handoff
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the conversation history and writes files to the operating system, creating an indirect prompt injection surface.
- Ingestion points: The skill processes the "current conversation," which may contain inputs from untrusted sources (SKILL.md).
- Boundary markers: No explicit delimiters or boundary markers are defined in the instructions to isolate the summarized data from the agent's instructions.
- Capability inventory: The skill utilizes file-writing capabilities to "Save to the temporary directory of the user's OS" (SKILL.md).
- Sanitization: The skill includes an explicit instruction to "Redact any sensitive information, such as API keys, passwords, or personally identifiable information" (SKILL.md).
Audit Metadata