csv-processor
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process CSV data which serves as an ingestion point for untrusted content that could contain malicious instructions.
- Ingestion points: CSV files and data patterns referenced in the description and trigger phrases (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions to help the agent distinguish between CSV data and instructions.
- Capability inventory: The skill allows extensive capabilities including unrestricted shell access (Bash cmd:*) and file system modifications (Write, Edit).
- Sanitization: No sanitization, validation, or escaping logic is described for the data being processed.
Audit Metadata