lazyweb
Fail
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: Multiple files including the root
README.md,SKILL.md, and several sub-skill instruction files (e.g.,skills/lazyweb-growth-score/SKILL.md) advise the agent to tell the user to runcurl -fsSL https://www.lazyweb.com/install.sh | bash. This pattern downloads and executes a remote shell script in the user's terminal without prior verification. - [DATA_EXFILTRATION]: The integrated browser utility contains logic in
browse/src/cookie-import-browser.tsto access sensitive local file paths, including browser cookie databases (e.g.,~/Library/Application Support/Google/Chrome/Default/Cookieson macOS and~/.config/paths on Linux). It also utilizes system tools likesecurity find-generic-password(macOS Keychain) andsecret-tool lookup(Linux) to retrieve the keys required to decrypt these cookies, posing a risk of unauthorized access to user session data. - [INDIRECT_PROMPT_INJECTION]: The
lazyweb-apply-design-best-practicesskill (inskills/lazyweb-apply-design-best-practices/SKILL.md) acts as a router that fetches instruction files from a wide range of third-party GitHub repositories (e.g.,emilkowalski/skills,addyosmani/web-quality-skills,resend/resend-skills). It explicitly instructs the AI agent to fetch these remote Markdown files and 'apply its rules, heuristics, and workflow as your operating best practices,' creating a significant surface for indirect prompt injection if any of the targeted repositories are compromised or contain adversarial instructions. - [COMMAND_EXECUTION]: Several Python scripts and Node.js components utilize
subprocess.runorspawnto execute CLI utilities such asgit,codex, and theclaudeCLI. Specifically,skills/lazyweb-design-create/generate-prototypes.pyexecutes commands via thecodextool, and thebrowseserver spawns theclaudeexecutable to handle background tasks. - [DYNAMIC_EXECUTION]: The
browsetool (inbrowse/src/read-commands.ts) implementsjsandevalcommands that allow for the runtime evaluation of arbitrary JavaScript code within a browser context using Playwright'spage.evaluatefunction.
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