better-result-migrate-v2
Fail
Audited by Gen Agent Trust Hub on Feb 13, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (HIGH): The skill possesses a high-risk attack surface because it ingests untrusted source code and performs file-write operations. Ingestion points: Workflow steps 1 and 2 (SKILL.md) identify user codebase files as input. Boundary markers: No delimiters or warnings are provided to separate data from instructions. Capability inventory: Workflow steps 3 through 6 involve writing and modifying files in the codebase. Sanitization: No sanitization or safety-filtering of processed code is specified.
Recommendations
- AI detected serious security threats
Audit Metadata