material-tracker

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface due to its ability to synchronize data from external Excel spreadsheets. Malicious instructions embedded in a synced spreadsheet could potentially manipulate the agent's logic for procurement tracking.
  • Ingestion points: Data is ingested from external files matching *SC*PO*Log*.xlsx or *SC-PO*.xlsx using the xlsx tool. The agent processes fields like 'Description', 'Vendor/Sub', and 'Notes' from these untrusted files.
  • Boundary markers: No specific delimiters or boundary instructions are used to separate ingested spreadsheet content from the agent's internal instructions.
  • Capability inventory: The skill can modify the project's procurement_log, generate alerts for the construction team, and initiate verification workflows that reference spec sections.
  • Sanitization: The instructions do not define any sanitization or validation logic for data extracted from external spreadsheets.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 06:53 AM
Security Audit — agent-trust-hub — material-tracker