cmo-advisor

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or exfiltration vectors were identified in the skill instructions or associated scripts.
  • [COMMAND_EXECUTION]: The skill references three local Python scripts used for marketing calculations. These scripts were reviewed and found to contain only benign data processing logic, using standard libraries for JSON parsing and mathematical operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests company context from a local file and marketing metrics from user-provided JSON. However, the limited capabilities of the associated tools (no network access, no arbitrary code execution) prevent this from being a significant security concern.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 11:10 PM