skills/lizard-build/skill/lizard/Gen Agent Trust Hub

lizard

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses a shell pipe to download and execute an installation script from the vendor's official domain (lizard.build). This is the primary method for setting up the required CLI environment.
  • [EXTERNAL_DOWNLOADS]: The bootstrap process fetches CLI installers and platform guides from the vendor's infrastructure.
  • [COMMAND_EXECUTION]: The skill executes shell commands using the Lizard CLI and npm to perform platform operations and manage local tool versions.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and follow instructions fetched dynamically from the lizard skills get core command. 1. Ingestion points: SKILL.md (Step 1). 2. Boundary markers: None present in the bootstrap logic. 3. Capability inventory: Shell command execution via CLI and package managers. 4. Sanitization: The skill relies on the integrity of vendor-provided CLI output without additional filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 12:41 PM