wtk-reuse-review
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including code diffs, repository files, and architectural documents. Malicious instructions embedded in these sources could influence the agent's analysis or reporting.
- Ingestion points: The skill reads a 'supplied diff range', 'named files/modules', and various documents such as the 'governing reuse policy and relevant product, architecture, and design contracts' as specified in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or warnings to treat ingested code or documentation as data rather than instructions.
- Capability inventory: The skill is primarily analytical and read-only. It uses 'existing search or repository tools' and a 'browser/evidence workflow' for UI verification, but contains no instructions for arbitrary subprocess execution, file-system modification (other than report generation), or network exfiltration.
- Sanitization: There is no evidence of sanitization or escaping mechanisms for the external content before it is processed by the agent.
Audit Metadata