Skills
skills/team-telnyx/skills/telnyx-ai-assistants-curl/Gen Agent Trust Hub

telnyx-ai-assistants-curl

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl to perform HTTP requests to the Telnyx API at api.telnyx.com. These commands are used to manage the lifecycle of AI assistants and interact with them during runtime.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted instructions and user messages.
  • Ingestion points: The instructions parameter in the Create an assistant and Update an assistant operations, as well as the message content in the Chat with an assistant operation (SKILL.md).
  • Boundary markers: Absent; the skill does not define delimiters or provide warnings to the agent to disregard embedded commands in the processed data.
  • Capability inventory: The skill can create, update, and delete AI assistants, tools, and MCP servers via API calls (SKILL.md).
  • Sanitization: Absent; the skill does not implement validation or escaping of the ingested instructions or chat content before inclusion in the API request body.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:01 AM