weekly-report-format

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's logic is focused on legitimate data aggregation and document formatting tasks for construction project management.
  • [COMMAND_EXECUTION]: The skill calls LibreOffice in headless mode to perform PDF conversions. This is a standard use of a well-known system utility and is appropriately restricted to its primary function.
  • [PROMPT_INJECTION]: While the skill processes data from external files (e.g., daily-report-data.json), which is a characteristic of indirect prompt injection surfaces, it implements standard processing workflows with no evidence of malicious instruction overrides or safety filter bypasses.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 09:53 PM
Security Audit — agent-trust-hub — weekly-report-format