telnyx-voice-advanced-curl

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides examples of using the standard curl utility to interact with REST APIs. This is consistent with the skill's stated purpose as a developer tool for call control.
  • [DATA_EXFILTRATION]: The skill demonstrates network operations targeting api.telnyx.com. These are legitimate communications with the vendor's official API infrastructure.
  • [PROMPT_INJECTION]: The skill describes webhook event processing where external data (such as DTMF digits or client state strings) is ingested into the agent's context. This represents a potential surface for indirect prompt injection if the agent interprets this data as instructions.
  • Ingestion points: Webhook payload fields documented in SKILL.md (e.g., data.payload.client_state, data.payload.digit).
  • Boundary markers: None specified in the documentation.
  • Capability inventory: Subprocess execution via curl for API actions.
  • Sanitization: No explicit sanitization or validation of webhook content is described in the reference material.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:01 AM