genkit-agents-js
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external data by calling documentation search tools (
search_genkit_docsandread_genkit_docs). This creates a vulnerability surface where instructions embedded in external documentation could influence agent behavior. - Ingestion points: SKILL.md (via search/read documentation tools).
- Boundary markers: None present in the skill instructions for tool outputs.
- Capability inventory: The skill allows for proposing, auditing, and editing code, as well as adding verification paths (tests/traces).
- Sanitization: No specific sanitization or filtering of documentation content is defined.
Audit Metadata