videocut-subtitle
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [Command Execution] (SAFE): The skill utilizes standard command-line tools (Whisper and FFmpeg) to perform video processing tasks. These operations are directly related to the skill's primary purpose.
- [Indirect Prompt Injection] (LOW): The skill possesses an attack surface for indirect prompt injection because it ingests and processes untrusted data from video transcripts.
- Ingestion points: Transcription results from
video.mp4and user-modified text drafts. - Boundary markers: None explicitly defined to separate the transcript data from the agent's instructions.
- Capability inventory: Subprocess execution of
whisperandffmpeg(viaSKILL.md). - Sanitization: No explicit sanitization is performed on the transcript text, though the workflow includes a 'User Review' step which serves as a manual checkpoint.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network communications were found.
Audit Metadata