skills/layerai/skills/layer-tilesets/Gen Agent Trust Hub

layer-tilesets

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the layerai/skills repository for resolving missing dependencies. This is an official resource owned by the skill's author and is used for intended platform functionality.
  • [COMMAND_EXECUTION]: Instructions guide the agent to suggest the command npx skills add layerai/skills --skill <name> to the user. This is a manual installation process for expanding the agent's capabilities using vendor-verified tools.
  • [REMOTE_CODE_EXECUTION]: The use of npx for installing skill-based dependencies constitutes a remote execution pattern; however, it is restricted to official vendor infrastructure and requires user initiation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions to form prompts for generative AI tools.
  • Ingestion points: User-supplied inputs for tile subject, material, and era in SKILL.md.
  • Boundary markers: None explicitly specified in the instruction set.
  • Capability inventory: Invocation of execute_forge for image generation and export_tileset for file packaging.
  • Sanitization: No specific sanitization or escaping logic is described for the prompt interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 06:45 PM