elevenlabs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text to generate audio assets and a timing manifest used for video composition. While this is a potential ingestion point for indirect instructions, it is considered safe as it is the primary function of the skill. Ingestion points: Text and prompt inputs in SKILL.md. Boundary markers: None. Capability inventory: File system writes and local command execution. Sanitization: No explicit sanitization.
- [COMMAND_EXECUTION]: The skill uses local utilities such as ffmpeg and a project-specific script tools/voiceover.py for audio processing and manifest generation.
Audit Metadata