cmo-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local Python scripts (marketing_budget_modeler.py and growth_model_simulator.py) for modeling scenarios. This functionality is restricted to local files included in the skill package and does not involve remote code execution or shell piping.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data which presents a theoretical injection surface.
- Ingestion points: The agent is instructed to read company-context.md before responding.
- Boundary markers: Absent; there are no specific instructions to ignore embedded prompts within the context file.
- Capability inventory: The agent can execute local modeling scripts based on the processed information.
- Sanitization: Absent; no explicit validation or filtering of the context data is documented.
Audit Metadata