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.
90
88%
Does it follow best practices?
Impact
92%
2.62xAverage score across 6 eval scenarios
Critical
Do not install without reviewing
The canonical home for this skill is agent-browser in vercel-labs/agent-browser
Security
1 critical severity finding. 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). Most of the URLs are benign/placeholder or official (example.com, github.com/login, lightpanda docs, localhost), but the list includes an explicit suspicious domain (https://malicious.com) and sites that could host installers or link to binaries, so the collection contains at least one high-risk download source and should be treated with caution.
Low
Low-risk findings.
1 low severity finding. 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
Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to navigate to arbitrary external URLs and ingest page content (e.g., "agent-browser open <url>" and "agent-browser snapshot -i" in SKILL.md and templates/capture-workflow.sh) so untrusted public web pages are read and used to decide subsequent interactions, enabling indirect prompt injection.
- Repository
- Intelligent-Internet/ii-agent
- Commit
0e57985
- 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.