Skills
skills/gooseworks-ai/gooseworks-ads-skills/create-concept-loop-video/Gen Agent Trust Hub

create-concept-loop-video

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies as having a surface for indirect prompt injection (Category 8).
  • Ingestion points: User-supplied strings from the loop_concept and states inputs (specifically the description and in_world_text fields) are ingested and used in Workflow Phase 2.
  • Boundary markers: The skill constructs a generation prompt by directly interpolating these user-controlled strings into a template without using delimiters or 'ignore' instructions to isolate the untrusted content.
  • Capability inventory: The skill's orchestration includes the execution of local Python scripts (extract_beats.py, render_edl.py), usage of the ffmpeg CLI for video processing, and network-based image generation via the fal API.
  • Sanitization: The instructions do not specify any validation, escaping, or filtering for user-provided strings before they are incorporated into the prompt logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:07 PM
Security Audit — agent-trust-hub — create-concept-loop-video