react-native-ease-refactor
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted project files, which creates a surface for indirect prompt injection where malicious instructions in code comments could potentially influence agent behavior.
- Ingestion points: In Phase 1, the skill uses Grep to scan and read files matching
**/*.{ts,tsx,js,jsx}. - Boundary markers: No specific delimiters or safety instructions are used to separate the ingested code content from the agent's internal reasoning logic.
- Capability inventory: The skill is authorized to rewrite and modify local files in Phase 5 to apply the migration.
- Sanitization: No sanitization or filtering of the source code is performed before it is analyzed for migration logic.
Audit Metadata