skills/team-telnyx/ai/telnyx-video-go/Gen Agent Trust Hub

telnyx-video-go

Fail

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The SKILL.md file contains a hardcoded JSON Web Token (JWT) within the RefreshClientToken code example. Hardcoded credentials pose a security risk of exposure.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the telnyx-go SDK from the official vendor repository github.com/team-telnyx/telnyx-go. This is a trusted vendor resource.\n- [INDIRECT_PROMPT_INJECTION]: The skill includes functions that ingest external data, creating a potential attack surface for indirect prompt injection.\n
  • Ingestion points: The UniqueName, room_id, session_id, and RefreshToken parameters used in API calls in SKILL.md.\n
  • Boundary markers: None are explicitly defined in the documented code snippets to delimit untrusted input.\n
  • Capability inventory: The skill possesses capabilities to create, modify, and delete video rooms and sessions, and to manage authentication tokens via the Telnyx API.\n
  • Sanitization: Relies on the standard telnyx-go SDK methods for API interaction.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 16, 2026, 04:56 PM