orx-reports
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and interpret external data to generate reports.
- Ingestion points: The skill instructions specify that the agent should 'Load orx-results when the report requires interpreting or comparing run results.'
- Boundary markers: There are no explicit instructions for using delimiters or boundary markers when handling data from external run results.
- Capability inventory: The skill allows the agent to write files (Markdown, CSV, PDF, SVG, Python scripts) directly into an
artifacts/directory. - Sanitization: The instructions do not detail any sanitization or validation steps for the content being processed from external run results into final reports.
Audit Metadata