react
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides architectural and coding guidelines that align with current React 19 best practices. It encourages the use of established tools such as ESLint, React Testing Library, and standard state management libraries.
- [INDIRECT_PROMPT_INJECTION]: The skill contains a 'Review' and 'Migrate' mode that ingests external code (diffs and project files) which constitutes an indirect prompt injection surface.
- Ingestion points: Source code and pull request diffs provided by users for review, refactoring, or migration tasks (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat ingested code as untrusted data or to ignore instructions embedded within the code.
- Capability inventory: The skill has the capability to write/modify files and suggests running codemods for migration (SKILL.md).
- Sanitization: There is no mention of sanitizing or validating the ingested code content before processing.
Audit Metadata