coo-advisor

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted data from external sources.
  • Ingestion points: Data enters through the platform's company-context.md file and user-provided JSON files processed by scripts/okr_tracker.py and scripts/ops_efficiency_analyzer.py.
  • Boundary markers: The skill does not implement delimiters or explicit instructions to isolate processed data from the agent's control context.
  • Capability inventory: The skill possesses capabilities for local file system operations, including reading context files and writing analytical reports.
  • Sanitization: Free-text fields from the input JSON (such as notes and titles) are included in the generated output without sanitization, which could potentially be used to influence the agent's following actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 08:16 AM
Security Audit — agent-trust-hub — coo-advisor