cdp
Drive Chrome via the DevTools Protocol from JavaScript. Run JS snippets through the `browser-harness-js` CLI — it auto-spawns a long-lived bun HTTP server holding a fully-typed CDP `Session`, and every call (`browser-harness-js 'await session.Page.navigate(...)'`) executes against the same persistent connection. Session, active target, and globals survive across calls. Use when the user wants to automate, script, or inspect a Chrome browser via CDP — single tab or multi-tab, attach to existing Chrome or to a new one launched with --remote-debugging-port.
80
100%
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
3 findings: 2 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
The bundle auto-installs Bun by curling and piping https://bun.sh/install to bash from the skill's bootstrap script (and references bun.sh elsewhere), which is a direct remote installer execution pattern that can deliver arbitrary binaries and is a high-risk download vector.
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
The code intentionally exposes a local eval server that can attach to a user's browser and provides explicit examples to read cookies, network bodies, iframe-contained secrets (e.g. card inputs), and even auto-installs a runtime via an unchecked curl | bash — these are high-risk, dual‑use capabilities that enable credential theft, data exfiltration, and supply‑chain compromise.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill instructs creating symlinks into system directories (e.g. /usr/local/bin) with a "may need sudo" note, and it auto-installs/auto-starts software (bun and a background server), which modifies the machine's state and can require elevated privileges.
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 skill ingests outsider-authored free text directly because the CLI `browser-harness-js '<JS>'`/stdin snippet is POSTed to the local REPL (`sdk/repl.ts`) via `/eval` and executed to produce CDP results, so any user-supplied snippet can be prompt-injection text fed to the agent’s runtime.
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 CLI script sdk/browser-harness-js directly runs a network fetch-and-execute (curl -fsSL https://bun.sh/install | bash), which fetches remote code at runtime and pipes it to a shell, so the skill executes external code from https://bun.sh/install.
- Repository
- browser-use/browser-harness-js
- Path
SKILL.md
- Commit
95b7a22
- 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.