lazyweb-growth-experiments

Fail

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructions in SKILL.md explicitly command the agent to download a script and pipe it directly to a shell interpreter.
  • Evidence: curl -fsSL https://www.lazyweb.com/install.sh | bash. This method provides no opportunity for the agent or user to verify the script's contents before it runs with the agent's privileges.
  • [EXTERNAL_DOWNLOADS]: The skill fetches executable content from an external domain (lazyweb.com) that is not associated with the developer or any trusted infrastructure.
  • [COMMAND_EXECUTION]: Uses the system shell to execute downloaded code and local health check commands (lazyweb_health).
  • [PROMPT_INJECTION]: The skill processes untrusted external data (growth experiments and A/B research) while having access to sensitive capabilities.
  • Ingestion points: External research data and A/B test evidence (SKILL.md).
  • Boundary markers: None.
  • Capability inventory: Shell command execution (curl, bash, lazyweb_health).
  • Sanitization: None.
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
CRITICAL
Analyzed
Aug 14, 2026, 04:23 AM
Security Audit — agent-trust-hub — lazyweb-growth-experiments