genkit-core-python
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external content through the search_genkit_docs and read_genkit_docs tools.
- Ingestion points: The SKILL.md file defines workflows that rely on data fetched by documentation tools.
- Boundary markers: There are no explicit delimiters or instructions provided to ignore potentially malicious or contradictory commands embedded within the retrieved documentation.
- Capability inventory: The instructions suggest the agent will perform audits, propose code edits, and execute verification paths, which provides a surface for fetched data to influence system operations.
- Sanitization: The skill does not specify any sanitization, validation, or filtering of the content returned by the documentation tools before it is processed by the agent.
Audit Metadata