viral-content-factory

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates Python scripts from predefined templates and executes them via the Bash tool. It also uses ffmpeg for video processing and concatenation. This automated workflow involves simple script generation from known templates.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of well-known libraries such as google-genai, Pillow, and fal-client. These are official packages from established service providers and are used as intended for media generation.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the interpolation of untrusted user data into AI generation prompts.
  • Ingestion points: User-provided inputs for 'Product' and 'Characters', and reference images in the ideas/ directory (SKILL.md).
  • Boundary markers: Templates use variable interpolation (e.g., CHARACTER_NAME), which structure the prompt but do not provide a security boundary against embedded instructions.
  • Capability inventory: The skill has access to shell execution via the Bash tool and file system modification via the Write tool.
  • Sanitization: No sanitization or content validation is performed on the user-supplied strings before they are incorporated into the prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 10:24 AM