deepgram
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches technical reference documentation from the vendor's domain at
https://www.pixazo.ai/models/deepgram.mdto define runtime parameters and error handling logic. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The agent is instructed in
SKILL.mdto load and process markdown content from an external vendor URL (https://www.pixazo.ai/models/deepgram.md). - Boundary markers: Absent. The skill does not provide delimiters or instructions for the agent to ignore potentially malicious commands embedded within the fetched documentation.
- Capability inventory: The skill logic in
SKILL.mdperforms local file system writes, modifies file permissions (chmod 600), and executes network requests usingcurl, the Pythonrequestslibrary, and the Node.jsfetchAPI to communicate withgateway.pixazo.ai. - Sanitization: Absent. The skill does not include validation or sanitization steps for the data retrieved from the remote documentation URL.
Audit Metadata