coo-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates Python scripts designed to ingest and analyze external JSON files, which represents an indirect prompt injection surface.
- Ingestion points: The scripts capacity_modeler.py, operational_kpi_tracker.py, and process_efficiency_scorer.py accept data via the --input parameter.
- Boundary markers: There are no instructions or delimiters provided to the agent to treat external data as untrusted or to ignore instructions embedded within the JSON values.
- Capability inventory: Script capabilities are restricted to local data processing and reporting; they lack network access, file-writing permissions, or code execution functions.
- Sanitization: Input data is handled using Python's standard json library.
Audit Metadata