genkit-tools-rag-python
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for a development and audit workflow related to Genkit. It does not include executable code, hardcoded credentials, or obfuscated content. The logic is purely instructional and relies on the agent's existing toolset for documentation retrieval.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Genkit documentation, which is an expected surface for this type of tool.
- Ingestion points: Data enters the context through
read_genkit_docscalls mentioned in SKILL.md. - Boundary markers: The skill does not explicitly define markers to separate retrieved documentation from instructions.
- Capability inventory: The agent is directed to build and audit code based on the retrieved documentation; no subprocess calls, file writes, or direct network operations are defined within the skill's own content.
- Sanitization: No specific sanitization or validation steps are prescribed for the retrieved content.
Audit Metadata