ai-product-photography

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an installation guide and related modules from the vendor's own GitHub organization and domain (inference-sh). These are official resources used for the intended functionality of the skill.
  • [COMMAND_EXECUTION]: The skill makes use of the infsh CLI tool via shell commands. These commands are constrained to the vendor's platform for generating images and perform no unauthorized or suspicious operations.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection in the 'Batch Generation' section, where user-supplied product descriptions are interpolated into shell command strings.
  • Ingestion points: User-provided strings for product names and angles in SKILL.md.
  • Boundary markers: None explicitly defined in the provided examples.
  • Capability inventory: Execution is restricted to the infsh command as defined in the allowed-tools metadata.
  • Sanitization: No explicit sanitization or escaping is shown in the examples, but the limited scope of the allowed tool significantly reduces the risk of malicious exploitation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 06:35 PM
Security Audit — agent-trust-hub — ai-product-photography