agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
86
84%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Security
3 findings — 1 critical severity, 1 high 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
Suspicious download URL detected (high risk: 0.70). The set contains an explicit malicious domain (https://malicious.com), several untrusted/unknown domains (site-a.com, site-b.com) and a third‑party install doc (lightpanda.io) that could lead to binary downloads, so while some entries are benign placeholders (example.com, app.example.com, github.com/login), the presence of a known malicious host and multiple unvetted sources makes this a potentially suspicious download surface.
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
Insecure credential handling detected (high risk: 0.90). The prompt contains multiple insecure patterns that require or demonstrate embedding secrets verbatim in commands or state files (e.g., inline passwords like agent-browser fill @e2 "password123", state files with plaintext session tokens, and examples that copy credentials), which creates an exfiltration 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: 0.90). The skill explicitly navigates arbitrary public URLs with "agent-browser open <url>" and ingests page content via snapshot/get text/eval as part of its core workflow and templates (see SKILL.md core workflow and templates/capture-workflow.sh), so untrusted third-party web content can be read and drive subsequent agent actions.
- Repository
- databricks/devhub
- Commit
6338825
- 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.