genkit-observability-js
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 and analyze external data, including documentation via
read_genkit_docsand arbitrary JavaScript/TypeScript code during the audit workflow. - Ingestion points:
search_genkit_docs,read_genkit_docs, and user-provided code files. - Boundary markers: None explicitly mentioned in the skill instructions to delimit untrusted documentation content.
- Capability inventory: The skill body does not explicitly use dangerous capabilities like file writes or network exfiltration, focusing on documentation lookup and code analysis.
- Sanitization: No specific sanitization or validation logic is defined for the content retrieved from the Genkit documentation or the code being audited.
Audit Metadata