browser-harness
Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.
75
92%
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
4 findings — 2 critical severity, 2 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
Suspicious download URL detected (high risk: 0.90). One URL is a direct remote shell script (https://browser-use.com/profile.sh) referenced for curl | sh installation, which is a high-risk distribution vector; the other links are docs, a GitHub repo, a local debug endpoint, or example pages and are not direct download sources.
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
Malicious code pattern detected (high risk: 0.90). This skill intentionally connects to the user's real browser and cloud profiles, includes an explicit example that extracts authenticated page content and writes it to disk, and directs installing a remote profile-sync script — capabilities that enable data exfiltration and present supply-chain risk.
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
Third-party content exposure detected (high risk: 0.75). SKILL.md’s required runtime workflow drives a real browser via CDP and then reads page content through `js(...)`/`page_info()` after navigating to a user-specified URL, which can ingest outsider-authored free text from arbitrary web pages into the agent’s LLM context.
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
Potentially malicious external URL detected (high risk: 0.80). The install/maintenance docs show fetching and running remote code — e.g., `git clone https://github.com/browser-use/browser-harness` (and the explicit install script `curl -fsSL https://browser-use.com/profile.sh | sh`) so the skill can pull and execute external code during install/update.
- Repository
- mishatojk/davidskills
- Commit
66860fb
- 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.