browser-auth
Documents how to use Chrome DevTools MCP to navigate authenticated web pages, extract data (tokens, configuration values), take screenshots, and handle login flows. Use when you need to interact with Buildkite, AWS Console, or other authenticated web UIs via the Chrome browser. Triggers when users ask about "browser auth", "extract token from browser", "navigate to buildkite", "chrome mcp", or need to scrape data from authenticated pages.
72
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This document explicitly instructs connecting to a user's live Chrome session (via DevTools MCP) to read DOM/clipboard contents and extract tokens/credentials (Buildkite, AWS, etc.) and even advises storing them in gitignored files and avoiding logs—constituting deliberate data exfiltration and credential-theft behavior.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly instructs the agent to extract tokens from page snapshots/DOM/clipboard and to write them into files, which requires the LLM/agent to receive and potentially emit secret values verbatim.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow uses Chrome DevTools MCP to fetch a user-authenticated target page and then reads its text content via snapshot/evaluate_script (browser-rendered accessibility tree and DOM text), which is outsider-authored free text from arbitrary third-party websites/console pages.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill configuration runs the command "npx -y chrome-devtools-mcp@latest --autoConnect" at runtime, which fetches and executes remote npm package code, so this is a runtime dependency that can execute remote code.
- Repository
- mock-server/mockserver-monorepo
- Commit
817ee95
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.