cmo-advisor

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run local Python scripts, specifically scripts/marketing_budget_modeler.py and scripts/growth_model_simulator.py, to perform budget modeling and growth simulations.
  • [PROMPT_INJECTION]: The skill implements a multi-agent research workflow that incorporates untrusted user-supplied data into prompts for sub-agents.
  • Ingestion points: User-supplied strings for {company}, {market}, and {challenge} are used in SKILL.md to populate prompts for research and planning tasks.
  • Boundary markers: The prompts do not include delimiters or instructions to ignore embedded commands within the user-provided data.
  • Capability inventory: The sub-agents are tasked with performing market research on external websites and generating 12-month marketing strategies.
  • Sanitization: There is no evidence of input validation, escaping, or content filtering for the data before it is interpolated into the sub-agent task prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:05 PM
Security Audit — agent-trust-hub — cmo-advisor