deepgram-rust-text-intelligence

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data by providing instructions for analyzing arbitrary text and content from remote URLs.
  • Ingestion points: The analyze_text and analyze_url methods in SKILL.md are used to process data from external sources.
  • Boundary markers: The provided code examples do not demonstrate the use of delimiters or explicit instructions to the AI to ignore instructions embedded within the processed text.
  • Capability inventory: The skill examples include the ability to perform network requests to Deepgram's API endpoints for text analysis.
  • Sanitization: The documentation does not specify sanitization or validation steps for the input text or URL content before it is sent for analysis.
  • [EXTERNAL_DOWNLOADS]: The skill mentions the installation of additional tools using npx skills add deepgram/skills for cross-language product knowledge.
  • Evidence: Reference to the Deepgram vendor's central skills repository in the final section of SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 04:43 PM