genkit-tutorials-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 untrusted content from external files and video summaries as part of the documented tutorial workflows.\n
- Ingestion points: PDF content and YouTube summaries are ingested into the agent context (SKILL.md).\n
- Boundary markers: There are no explicit instructions to use delimiters or warnings to ignore instructions embedded within the ingested data.\n
- Capability inventory: The skill uses
search_genkit_docsandread_genkit_docstools to facilitate the audit and build processes.\n - Sanitization: The instructions do not define methods for sanitizing or validating external content before processing.
Audit Metadata