material-procurement-tracker

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by design, as it ingests untrusted data from external files which could potentially influence agent behavior or filesystem operations. * Ingestion points: The instructions.md file directs the agent to accept project data in CSV, Excel, and JSON formats. * Boundary markers: There are no explicit delimiters or instructions to ignore commands within the ingested data. * Capability inventory: SKILL.md provides filesystem write access through pandas.to_excel for logging procurement data. * Sanitization: The implementation lacks explicit validation or sanitization logic for the data content before it is processed or exported.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:28 AM