cwicr-value-engineering

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted construction data from external sources.
  • Ingestion points: Data enters the agent context through CSV, Excel, and JSON files as described in the instructions.
  • Boundary markers: The prompt instructions lack clear delimiters or specific directives to the AI to ignore instructions embedded within the ingested data.
  • Capability inventory: The skill has permissions to read datasets and write Excel reports to the filesystem using the pandas library.
  • Sanitization: No specific text sanitization or filtering logic is implemented for the data fields before they are processed by the LLM.
  • [EXTERNAL_DOWNLOADS]: The skill includes documentation links and resource references to the author's official GitHub repository and website.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:28 AM