movie-maker
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS] (CRITICAL): Automated scanner URLite flagged 'rules/start/requirements.md' for containing a blacklisted URL (signature: UR4EFAFDCAD26E3E52-0200).
- [COMMAND_EXECUTION] (MEDIUM): The skill instructs the agent to construct and run shell commands (ffmpeg, curl) using variables derived from user input and API responses, which can lead to command injection (see rules/render/rendering.md).
- [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection. 1. Ingestion points: Intake questions in SKILL.md and rules/start/start-here.md. 2. Boundary markers: Absent. 3. Capability inventory: Execution of subprocesses (ffmpeg) and network requests (curl). 4. Sanitization: Absent.
- [DATA_EXFILTRATION] (LOW): Sensitive provider API keys are transmitted to non-whitelisted domains (fal.run, elevenlabs.io) via curl headers.
Recommendations
- AI detected serious security threats
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata