cro-review

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local Python scripts (revenue_forecast_model.py and churn_analyzer.py) via the shell. These scripts are located in relative directories within the broader advisor tool suite.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided data via the parameter to generate business insights. While the skill processes external input, it does not demonstrate malicious intent.
  • Ingestion points: The argument in the /cs:cro-review command described in SKILL.md.
  • Boundary markers: None explicitly defined in the skill documentation to delimit user input.
  • Capability inventory: Execution of Python scripts (revenue_forecast_model.py, churn_analyzer.py) in SKILL.md.
  • Sanitization: No sanitization or validation logic is present in the markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:45 PM
Security Audit — agent-trust-hub — cro-review