csv-processor
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external CSV files whose content is returned to the AI agent's context without sanitization, creating a potential surface for indirect prompt injection if the files contain malicious instructions.\n
- Ingestion points:
scripts/csv_processor.pyreads user-specified CSV files using theread_csvfunction.\n - Boundary markers: None identified; the output is printed directly to stdout for the agent to consume without delimiters or specific ignore instructions.\n
- Capability inventory: The script performs local file system operations (read and write) and text manipulation using standard libraries (
csv,json,re).\n - Sanitization: The tool does not validate or sanitize cell content for potentially executable instructions or prompt injection patterns before outputting results.
Audit Metadata