telnyx-ai-assistants-python

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data through chat messages and configuration parameters which could contain instructions designed to manipulate agent behavior (Indirect Prompt Injection).
  • Ingestion points: The content parameter in client.ai.assistants.chat() and the instructions parameter in client.ai.assistants.create() (found in SKILL.md).
  • Boundary markers: The skill does not implement or recommend delimiters or safety instructions to isolate untrusted content.
  • Capability inventory: The skill provides access to resource deletion (client.ai.assistants.delete()), SMS messaging (client.ai.assistants.send_sms()), and external tool integration via MCP (client.ai.mcp_servers.create()) in SKILL.md.
  • Sanitization: There is no evidence of input validation, filtering, or escaping for user-provided strings.
  • [COMMAND_EXECUTION]: The client.ai.mcp_servers.create method allows for the configuration of Model Context Protocol servers using a URL, enabling the agent to dynamically extend its capabilities with external tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 11:36 PM