deepgram-recipes
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches code snippets and documentation from Deepgram's official GitHub repository (github.com/deepgram/recipes). This is a well-known technology service and the source is considered trustworthy.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from an external repository, creating a potential surface where embedded instructions could influence the agent. However, the risk is minimal given the trusted nature of the source.
- Ingestion points: Retrieves documentation and code from
github.com/deepgram/recipes. - Boundary markers: The instructions do not define explicit delimiters to isolate external content from the agent's system prompt.
- Capability inventory: The skill is limited to documentation retrieval and code presentation; it does not involve automated command execution, file writing, or network operations on the ingested data.
- Sanitization: No specific filtering or sanitization of the retrieved content is defined in the skill instructions.
Audit Metadata