apply-ui-review
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality relies on processing external UI review reports and goal packages which provide instructions for code changes.
- Ingestion points: UI review reports and goal packages identified in the repository (SKILL.md, Step 1).
- Capability inventory: The skill modifies source code, interacts with local development tools (pnpm, git), and captures screenshots (SKILL.md, Steps 3-5).
- Boundary markers: No specific delimiters are used to separate the external report content from the agent's instructions.
- Sanitization: The skill does not describe any sanitization or validation of the instructions contained within the reports.
- [COMMAND_EXECUTION]: The skill executes local development commands such as pnpm for testing, linting, and building the project.
- Evidence: Explicit instructions to run 'pnpm test', 'pnpm lint', and 'pnpm typecheck' are found in the self-check section of SKILL.md and the record contract.
Audit Metadata