plain-design-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by analyzing project files to inform its design decisions.\n
- Ingestion points: In SKILL.md, the agent is tasked with inspecting existing design systems, Tailwind configurations, API examples, and logs within the user's repository.\n
- Boundary markers: No specific delimiters are used to separate untrusted project content from the agent's instructions.\n
- Capability inventory: The agent is empowered to modify frontend code and execute local verification commands.\n
- Sanitization: The skill does not specify any sanitization or validation of the files it reads before processing them.\n- [COMMAND_EXECUTION]: The skill instructions involve the execution of shell commands to validate implementation.\n
- Evidence: The references/implementation-checklist.md directs the agent to execute repository formatters and start development servers.
Audit Metadata