Skills
Navigate
skills/thaddeushackz/the-ai-video-editor/opus-gpt-director/Gen Agent Trust Hub

opus-gpt-director

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell scripts (setup-toolchain.sh, hf-env.sh) and utilize various command-line interfaces for video production, including ffmpeg, ffprobe, hyperframes, and remotion.
  • [INDIRECT_PROMPT_INJECTION]: The workflow ingests untrusted data from project files. 1. Ingestion points: ledger.json (Gate 5) and VIDEO_BRIEF_TEMPLATE.md (Gate 1). 2. Boundary markers: Absent. 3. Capability inventory: Includes bash script execution, node verification scripts, and media rendering tools. 4. Sanitization: Absent. This represents a potential surface for indirect prompt injection if project data is malicious.
  • [SAFE]: No evidence of malicious behavior, obfuscation, or data exfiltration was found. The skill's operations are consistent with its professional video engineering purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 02:06 PM