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.
88
85%
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
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
The URL list includes https://malicious.com, an untrusted domain explicitly flagged in the skill (example shows it as blocked) and therefore represents a high-risk suspicious download/source that could distribute 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
The skill includes examples that place plaintext secrets directly into commands (e.g., agent-browser fill "password123" and echo "pass" | ...), which would require the LLM to emit secret values verbatim and thus poses an exfiltration risk.
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
In SKILL.md, the required workflow uses `agent-browser open <url>` followed by `agent-browser snapshot -i` (and optionally `get text body`) which ingests free text from the navigated web page, i.e., outsider-authored page content without pre-selecting a specific item.
- Repository
- rivet-dev/sandbox-agent
- Commit
bbc195c
- 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.