cto-review
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts to analyze technical debt and team scaling.
- Evidence: Found in SKILL.md, the instructions trigger the execution of
python ../../../skills/cto-advisor/scripts/tech_debt_analyzer.pyandpython ../../../skills/cto-advisor/scripts/team_scaling_calculator.py. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted architectural plans, creating a surface for indirect prompt injection.
- Ingestion points: The
<plan>argument provided to the/cs:cto-reviewcommand in SKILL.md. - Boundary markers: The skill does not implement delimiters (e.g., XML tags or triple quotes) or specific instructions to the agent to ignore potentially malicious content within the plan.
- Capability inventory: The skill has the capability to execute Python scripts via the shell, which are then used to generate output for the CTO review report.
- Sanitization: There is no evidence of input validation, escaping, or filtering of the provided architectural plan content before processing.
Audit Metadata