video-editing

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface exists via the transcript-based editing feature.
  • Ingestion points: Video transcripts from recording_transcripts.segments_json (untrusted external data) are processed by an AI agent to propose editing cuts.
  • Boundary markers: No explicit delimiters or boundary markers for the transcript data are defined in this skill's instructions.
  • Capability inventory: The skill utilizes ffmpeg.wasm for client-side rendering, enqueues server-side export jobs, and performs database writes to recordings.edits_json and recordings.chapters_json.
  • Sanitization: The skill specifies that edit actions validate for non-overlapping ranges and throw errors on invalid input. Crucially, agent-proposed edits are written to a draft state (editor-draft) for human review and explicit approval before being committed.
  • [EXTERNAL_DOWNLOADS]: Lazy-loads the well-known @ffmpeg/ffmpeg library and associated WASM binaries for client-side video processing when the user initiates an export.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:51 AM
Security Audit — agent-trust-hub — video-editing