browser-devtools-cli
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADS
Full Analysis
- Persistence (HIGH): The documentation instructs users to modify shell profiles like
~/.bashrcor~/.zshrcwitheval \"$(browser-devtools-cli completion bash)\". This allows the tool to execute code automatically at the start of every shell session, creating a persistence vector. - Indirect Prompt Injection (LOW): The skill is designed to process untrusted content from the web, which may contain malicious instructions. Evidence Chain: 1. Ingestion points:
navigation go-toandcontent get-as-text. 2. Boundary markers: Absent; no instructions are provided to the agent to distinguish between tool output and page content. 3. Capability inventory: The skill usesBashto execute commands, allowing for network access and file system interaction. 4. Sanitization: No sanitization or escaping of web content is performed. - Credentials Unsafe (LOW): Example code in the skill documentation contains a hardcoded password string (
password123). - External Downloads (MEDIUM): The skill requires installing an unverified package from the public npm registry (
browser-devtools-mcp). - Command Execution (LOW): The skill utilizes the Bash tool to run its core CLI functions, giving it extensive control over the browser environment and local state.
Recommendations
- AI detected serious security threats
Audit Metadata