elevenlabs
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes text prompts to generate audio, sound effects, and music, creating a surface for indirect prompt injection if untrusted data is passed to the generation functions. Ingestion points: Untrusted text is passed to text-to-speech, sound effects, and music generation functions in SKILL.md. Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the input text. Capability inventory: The skill writes audio files to the local file system (e.g., voiceover.mp3) and invokes a local Python script
tools/voiceover.py. Sanitization: No explicit sanitization or validation of the input text is provided in the skill scripts. - [COMMAND_EXECUTION]: The skill instructions include the execution of a local tool via the command line (
python tools/voiceover.py) to automate scene-based audio generation.
Audit Metadata