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.
91
92%
Does it follow best practices?
Impact
90%
3.60xAverage score across 3 eval scenarios
Critical
Do not install without reviewing
The canonical home for this skill is agent-browser in vercel-labs/agent-browser
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.
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). These links include an explicitly suspicious domain (malicious.com), several untrusted/unknown domains and local endpoints, and none are clearly official package/download pages (no trusted vendor CDNs or package manager links), so the set represents a moderate-to-high risk for distributing malware.
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 explicit examples that embed plaintext credentials verbatim in CLI commands (e.g., agent-browser fill @e2 "password123" and chained commands with literal passwords), which would require the LLM to output secret values directly even though safer alternatives are also mentioned.
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 navigates and ingests arbitrary public web content (e.g., SKILL.md commands like "agent-browser open <url>", "agent-browser snapshot -i", "agent-browser get text body" and templates such as templates/capture-workflow.sh and templates/form-automation.sh) and by default imposes no restrictions, so untrusted third-party pages can be read and directly influence agent actions.
- Repository
- gsd-build/gsd-2
- Commit
33c00aa
- 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.