genkit-tools-rag-js
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external JavaScript/TypeScript code and Genkit documentation via tools like search_genkit_docs and read_genkit_docs, which creates a surface for indirect prompt injection if those sources contain malicious instructions.
- Ingestion points: External code provided by the user for auditing and documentation retrieved via external search tools.
- Boundary markers: None explicitly defined in the instructions to separate external data from system instructions.
- Capability inventory: The skill instructs the agent to audit and propose code changes; it does not request file system write, network, or shell execution capabilities itself.
- Sanitization: No specific sanitization or filtering of input content is mentioned.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata. It does not include any scripts, binaries, or executable code, which significantly reduces the direct attack surface.
Audit Metadata