Skills
Navigate
skills/wix/skills/wix-headless-fast/Gen Agent Trust Hub

wix-headless-fast

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources to populate the site backend during the seeding phase.\n
  • Ingestion points: SKILL.md (Step 2: "The seed plan") describes processing supplied content like CSVs, spreadsheets, and catalog links.\n
  • Capability inventory: The skill uses setup.mjs and attach.mjs to execute shell commands (spawn) and perform network requests (fetch) against Wix management APIs.\n
  • Sanitization: Data sanitization logic is not present in the provided management scripts and is handled by vertical-specific seeding logic.\n
  • Boundary markers: The skill does not provide specific instructions to the agent for using delimiters or ignoring instructions embedded within user-supplied data files.\n- [EXTERNAL_DOWNLOADS]: The skill fetches resources from the official vendor's infrastructure.\n
  • cold-start.md downloads the bootstrap.mjs script from the official Wix website (wix.com).\n
  • templates.mjs clones site templates from the official Wix GitHub repository (github.com/wix/skills.git).\n- [REMOTE_CODE_EXECUTION]: The skill executes a remotely fetched script to initialize the environment.\n
  • During the cold start phase, the agent is instructed to download and run the bootstrap.mjs script from the Wix domain to manage CLI login.\n- [COMMAND_EXECUTION]: The skill performs extensive shell command operations for project orchestration.\n
  • Scripts like setup.mjs and attach.mjs execute npm create, npx, and git to scaffold the project, install dependencies, and manage site configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 10:32 PM