lazyweb-apply-design-best-practices

Fail

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill contains a fallback instruction directing the agent to tell the user to run curl -fsSL https://www.lazyweb.com/install.sh | bash if a tool is missing. This pattern is extremely high risk as it social-engineers the user into executing unverified code from an external, untrusted domain directly in their terminal.
  • [PROMPT_INJECTION]: The skill operates as a router that fetches and adopts instructions from external third-party repositories, making it highly vulnerable to indirect prompt injection.
  • Ingestion points: The skill fetches SKILL.md files from multiple untrusted GitHub repositories (e.g., github.com/emilkowalski/skill, github.com/LottieFiles/motion-design-skill, github.com/nextlevelbuilder/ui-ux-pro-max-skill) using WebFetch or lazyweb_fetch_best_practice.
  • Boundary markers: None. The skill instructs the agent to "read content in full" and "apply its rules, heuristics, and workflow as your operating best practices" immediately after fetching.
  • Capability inventory: The skill has access to sensitive tools including Bash, Read, Write, WebFetch, and Agent, which could be exploited by malicious instructions in fetched content.
  • Sanitization: None. There is no validation or filtering of the external content before it is incorporated into the agent's operating context.
Recommendations
  • HIGH: Downloads and executes remote code from: https://www.lazyweb.com/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 8, 2026, 03:07 PM
Security Audit — agent-trust-hub — lazyweb-apply-design-best-practices