solution-design
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill invokes a local Python module
skills.solution_design.designfor workflow orchestration. This is a standard and intended function of the skill, limited to its own script directory. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill ingests user-provided problems for parallel analysis without explicit sanitization. 1. Ingestion points: User input via problem statements (README.md). 2. Boundary markers: Absent. 3. Capability inventory: Python subprocess execution (SKILL.md). 4. Sanitization: Absent.
- [PROMPT_INJECTION] (LOW): The skill utilizes directives like 'IMMEDIATELY invoke' and 'Do NOT explore first' in SKILL.md to override the agent's default reasoning and exploratory behavior. While functional for this skill, these are behavior-override patterns.
Audit Metadata