Skills
Navigate
skills/guyronnen/openmontage/text-to-speech/Gen Agent Trust Hub

text-to-speech

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text input from users or external sources to generate speech audio, which represents an indirect prompt injection surface.
  • Ingestion points: The text parameter in the text_to_speech function and API calls within SKILL.md.
  • Boundary markers: None present in the documentation or code examples to delimit user content from instructions.
  • Capability inventory: The skill can perform network operations (POST/GET) to api.heygen.com and provides URLs for file downloads from resource.heygen.ai and resource2.heygen.ai.
  • Sanitization: No explicit sanitization, filtering, or validation of the input text is implemented in the provided snippets.
  • [SAFE]: All network communications target official HeyGen API and resource domains. The skill correctly instructs the use of environment variables (HEYGEN_API_KEY) for secret management, avoiding hardcoded credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:09 AM
Security Audit — agent-trust-hub — text-to-speech