elevenlabs-tts

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied text strings to generate audio, which presents a surface for indirect prompt injection attacks where malicious instructions could be embedded in the text.
  • Ingestion points: The 'text' field in the JSON input used with the belt CLI in SKILL.md.
  • Boundary markers: Absent; there are no delimiters used to distinguish untrusted data from instructions.
  • Capability inventory: The skill utilizes the belt CLI via Bash (as restricted in allowed-tools) to execute audio generation tasks.
  • Sanitization: No sanitization or validation of the input text is described in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill references external installation instructions and related skills from the vendor's official GitHub repository.
  • Evidence: Reference to cli-install.md on raw.githubusercontent.com and the use of npx to add skills from the inference-sh namespace.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 09:33 AM
Security Audit — agent-trust-hub — elevenlabs-tts