genkit-architecture-js
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data by instructing the agent to fetch and read official documentation using tools.
- Ingestion points: The skill relies on the output of
search_genkit_docsandread_genkit_docs(referenced in SKILL.md). - Boundary markers: There are no explicit delimiters or instructions to the agent to disregard malicious directives that might be present in the fetched documentation.
- Capability inventory: The skill is primarily instructional for design and auditing; it does not contain built-in file-write, network-send, or code-execution capabilities, limiting the potential impact of an injection.
- Sanitization: No sanitization or validation of the content returned by the documentation tools is specified.
Audit Metadata