enterprise-press-batch

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the gen-ai CLI and exiftool utility to handle batch image processing, upscaling, and metadata stamping. These commands are standard for the skill's stated purpose of media asset management.
  • [PROMPT_INJECTION]: The skill processes user-defined prompts ($HERO_PROMPT) and local image data from ./sources/, representing an indirect prompt injection surface.
  • Ingestion points: Reads image files and manifest parameters from the local file system and specified project directories.
  • Boundary markers: Recommends the use of a brand governance framework (brand.md) to restrict the scope and style of AI-generated content.
  • Capability inventory: Performs local file read/write operations, metadata modification, and cloud storage uploads via platform-integrated CLI tools.
  • Sanitization: Relies on external brand governance skills for content control; does not explicitly demonstrate shell-level sanitization for environment variables used in CLI prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 12:52 AM
Security Audit — agent-trust-hub — enterprise-press-batch