telnyx-voice-gather-java

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external callers, which could potentially be used to influence the behavior of the AI assistant.
  • Ingestion points: Caller data is ingested via gather and gatherUsingAi methods in SKILL.md.
  • Boundary markers: No explicit boundary markers or delimiters are demonstrated in the examples to isolate caller input from agent instructions.
  • Capability inventory: The skill has access to call control actions including starting/stopping assistants and sending messages via the Telnyx SDK.
  • Sanitization: The documentation does not demonstrate sanitization or validation of the gathered caller input before further processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 06:27 PM
Security Audit — agent-trust-hub — telnyx-voice-gather-java