eval-skill
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No executable code, scripts, or network operations were found in the provided files. The skill functions as a documentation and evaluation repository.- [INDIRECT_PROMPT_INJECTION]: The skill processes CSV data from external files. While the provided sample data is benign, processing untrusted CSV content represents a potential injection surface.
- Ingestion points: evals/files/sample.csv referenced in evals.json.
- Boundary markers: Absent in the instructions.
- Capability inventory: No tools or active scripts are defined.
- Sanitization: No sanitization logic is present.
Audit Metadata