cmo-review
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's workflow involves executing Python scripts via a bash command block. Specifically, it runs
marketing_budget_modeler.pyandgrowth_model_simulator.pylocated in relative paths within the project structure. - [INDIRECT_PROMPT_INJECTION]: The skill accepts a
<plan>argument which is untrusted user-supplied data. - Ingestion points: The
<plan>variable is passed to the CMO review command and processed by the agent (SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to treat the plan content as untrusted data.
- Capability inventory: The skill has the ability to execute local Python scripts via subprocess calls in the workflow (SKILL.md).
- Sanitization: There are no documented sanitization or validation steps for the input plan before it is processed by the agent.
Audit Metadata