cpo-review
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts to facilitate product management analysis:
python product-team/skills/product-manager-toolkit/scripts/rice_prioritizer.pyfor RICE scoring.python ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/cpo-advisor/scripts/pmf_scorer.pyfor product-market fit scoring.python ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/cpo-advisor/scripts/portfolio_analyzer.pyfor portfolio analysis.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied roadmap data through the
<plan>parameter. This creates a surface where embedded instructions could potentially influence the agent, although the risk is low due to the intended analytical context. - Ingestion points: User input passed via the
<plan>command argument. - Boundary markers: No explicit delimiters are used to wrap the input data.
- Capability inventory: Executes subprocesses via Python and reads local script files.
- Sanitization: No input sanitization or filtering is observed in the provided instructions.
Audit Metadata