vibe-slice-migrator
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and processes source code from the repository. Adversarial instructions hidden in comments within the legacy code could attempt to influence the agent's behavior during the migration process.\n
- Ingestion points: Legacy code files and project specification files (
specs/REQS.md) processed during the migration loop.\n - Boundary markers: The skill does not employ specific delimiters or 'ignore' instructions when reading legacy file content.\n
- Capability inventory: The agent uses
BashandWritetools to analyze and rewrite files on the system.\n - Sanitization: There is no evidence of code sanitization or filtering to remove potential instructions before the agent processes the files.\n- [SAFE]: The 'Step 0' safety pre-check explicitly prevents modification of sensitive code paths (Auth, Billing, Crypto, Compliance), which is a key defensive design feature.
Audit Metadata