react-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a React specialist that analyzes and modifies code within a workspace, creating a surface for indirect prompt injection.
- Ingestion points: The agent processes code files and tasks provided in the workspace environment as defined in SKILL.md.
- Boundary markers: The instructions lack explicit directives for the agent to ignore or isolate instructions found within user-provided content.
- Capability inventory: The skill metadata identifies workspace-write permissions, allowing the agent to modify the file system based on its interpretation of the workspace content.
- Sanitization: No input validation or sanitization routines are specified for handling the code being processed.
Audit Metadata