output
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and workflow guidance for using the Kubb code generator. All referenced resources, including documentation links and configuration files, are standard for this development tool and its vendor.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local project files to discover configuration and exports. Ingestion points: kubb.config.ts and generated files under output.path (SKILL.md). Boundary markers: None present. Capability inventory: File reading and directory listing. Sanitization: None present. The risk is considered safe as the ingestion source is the user's local project configuration and generated artifacts rather than untrusted external data.
Audit Metadata