handoff
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading an existing handoff document to gather context, which provides a surface for indirect prompt injection if that file contains malicious instructions.
- Ingestion points: Reads the HANDOFF.md file in Step 2.
- Boundary markers: No delimiters or specific instructions are provided to the agent to distinguish between data and potential instructions in the handoff file.
- Capability inventory: The skill has file system access to read and write within the project directory.
- Sanitization: There is no sanitization or validation of the data retrieved from the file.
Audit Metadata