genkit-flows-python
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a structured workflow for developers to build or audit Genkit code using provided tools for searching and reading documentation. No signs of prompt injection, data exfiltration, or malicious command execution were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from external documentation sources using the
read_genkit_docstool. - Ingestion points: External data is ingested via the
read_genkit_docstool as specified in the 'Source of truth' section of SKILL.md. - Boundary markers: The instructions do not specify boundary markers or delimiters for the ingested content.
- Capability inventory: The skill does not contain instructions for subprocess execution, network operations (beyond the search tools), or file writing.
- Sanitization: There are no explicit instructions to sanitize or validate the content returned by the documentation tools.
Audit Metadata