telnyx-ai-assistants-javascript

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the official 'telnyx' npm package, which is a verified vendor resource for accessing Telnyx services.
  • [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection through its interaction with the Telnyx AI API.
  • Ingestion points: Assistant configurations, including instructions and descriptions, are ingested via the client.ai.assistants.retrieve() and client.ai.assistants.list() methods in SKILL.md.
  • Boundary markers: The skill does not implement boundary markers or instructions for the agent to ignore embedded commands within the retrieved metadata.
  • Capability inventory: The skill possesses extensive capabilities to create, update, and delete cloud resources like assistants and MCP servers, as documented in SKILL.md and references/api-details.md.
  • Sanitization: There is no evidence of data validation or sanitization of the content retrieved from the API before it enters the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 05:53 PM