discovery-interview-prep
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read persona files, user research directories, and specification documents to generate interview guides. If these files contain malicious instructions, the agent could potentially execute them or produce harmful output.
- Ingestion points: The skill reads from persona files, user research directories, and project specification files (specifically the Risks/Assumptions section).
- Boundary markers: None specified in the instructions to delimit external file content or warn the agent to ignore embedded instructions.
- Capability inventory: The skill primarily performs file read and text generation operations. It does not explicitly define subprocess calls or network operations in the provided markdown, but standard agent tools for reading and writing files are implied.
- Sanitization: No sanitization, escaping, or validation logic is defined for the content read from external files.
Audit Metadata