product-engineer-agent
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts to generate technical documentation and product visualizations. These scripts, located via environment variables such as ${CLAUDE_PLUGIN_ROOT} and ${SKILL_PATH}, are part of the skill's core functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input regarding product concepts and constraints, which are then used to build prompts for image generation tools.
- Ingestion points: User responses to discovery questions in Step 1 of the workflow.
- Boundary markers: None; user input is interpolated directly into prompt templates without delimiters.
- Capability inventory: The skill can execute local scripts via subprocesses with CLI arguments.
- Sanitization: No explicit sanitization or validation logic is defined for the user-provided strings before they are used in command-line arguments.
Audit Metadata