genkit-evaluation-python
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and follow external documentation via
search_genkit_docsandread_genkit_docs, creating an attack surface where malicious content in those documents could influence agent behavior. - Ingestion points: External Genkit documentation fetched at runtime via tool calls specified in
SKILL.md. - Boundary markers: The instructions lack delimiters or specific directives to ignore potentially malicious instructions embedded within the external documentation.
- Capability inventory: The skill encourages the agent to generate implementations, schemas, and verification paths (tests/evaluations) based on the fetched content.
- Sanitization: There are no instructions to sanitize or validate the content retrieved from the documentation tools.
- [NO_CODE]: The skill consists solely of documentation and instructions in
SKILL.mdand does not include any accompanying scripts, binaries, or configuration files that could hide executable malicious payloads.
Audit Metadata