Skills
Navigate
skills/awesome-genmedia/skills/ai-catalog-generator/Gen Agent Trust Hub

ai-catalog-generator

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of curl for interacting with the each::sense API and provides a batch processing shell script to automate image generation requests.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with an external API hosted at eachsense-agent.core.eachlabs.run and provides links to eachlabs.ai for authentication keys and product documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a processing layer for user-provided product descriptions and reference images which are then used as prompts for an external image generation service.
  • Ingestion points: The messages content field in the curl and Python code snippets within SKILL.md acts as an entry point for untrusted user input.
  • Boundary markers: No explicit prompt-level delimiters are suggested in the provided examples; the skill relies on the API's structured request format.
  • Capability inventory: The skill is configured with Bash(curl *) and WebFetch capabilities.
  • Sanitization: The provided examples do not include logic for sanitizing or validating user-provided strings before they are included in API requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 05:22 AM