react-specialist
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and modifies external React source code and module boundaries, establishing an ingestion point for untrusted data that could contain malicious instructions.
- Ingestion points: The skill analyzes 'module/path' and 'execution boundaries' of React source code provided in the workspace (SKILL.md).
- Boundary markers: Absent; the instructions do not define specific delimiters or warn the agent to ignore instructions embedded in code comments or strings.
- Capability inventory: Metadata specifies 'sandbox_mode: workspace-write', allowing the skill to modify files in the environment (SKILL.md).
- Sanitization: Absent; there are no instructions to validate or filter the content of analyzed source files before processing or modification.
Audit Metadata