coo-advisor

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate business operational tools. Technical analysis of the provided Python scripts (scripts/okr_tracker.py, scripts/ops_efficiency_analyzer.py) and reference documents found no security concerns.
  • [COMMAND_EXECUTION]: The skill utilizes local Python scripts for data analysis. These scripts are self-contained, do not perform network operations, and use standard libraries for processing user-supplied JSON data.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection. Ingestion points: Data is ingested from okrs.json and data.json via script arguments and from company-context.md as mentioned in SKILL.md. Boundary markers: No explicit delimiters are specified for the ingested content. Capability inventory: The skill executes Python scripts and performs standard file read/write operations. Sanitization: No sanitization is performed on the ingested data, which is parsed as JSON or read as markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 12:32 PM
Security Audit — agent-trust-hub — coo-advisor