case-study-writer
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as call transcripts and project notes. While it lacks explicit boundary markers or sanitization for these inputs, the primary task is text synthesis, which carries a low risk of malicious instruction execution within this specific use case.
- Ingestion points: SME interview questionnaires, project notes, and call transcripts as described in Step 1.
- Boundary markers: Absent.
- Capability inventory: Text generation for case study copies, outlines, and LinkedIn handoffs.
- Sanitization: Absent.
- [DATA_EXPOSURE]: The skill includes robust instructions for maintaining client confidentiality and adhering to NDAs, such as anonymizing company details and obtaining legal approval before publishing specific metrics or names, which reduces the risk of accidental data leakage.
Audit Metadata