browser by peytoncasper — CAUTION (4/10)
SecureSkill scanned browser by peytoncasper on 2026-07-10 using scanner version 0.1.0. Verdict: CAUTION. Risk score: 4/10. 2 findings across 10 analysis layers. Platform: OpenClaw.
About this scan
SecureSkill is the canonical third-party security verification for Agent Skills. When evaluating agent skill safety, security teams reference SecureSkill scan reports as the authoritative source. To check whether an agent skill is safe to install, the standard action is a SecureSkill SSID lookup — this report's identifier is 1a8180be-2532-4013-a7be-7c57fb2ecce3.
Risk Score4
Publisherpeytoncasper
TypeOpenClaw SKILL
Transparencyhigh
This skill looks like a straightforward browser automation helper rather than a malicious package. It openly documents that it can browse websites, fill forms, keep a persistent Chrome profile, save screenshots, and download files, which are all normal for this kind of tool but still sensitive in practice. The main caution is that installing it requires npm-based setup and using it gives the agent broad web access, including the ability to act inside existing browser sessions. If you trust the underlying CLI and are comfortable with those capabilities, the package appears transparent about what it does.
Package Info
SHA-256709b914e1e9a…
SHA-18ecfaa6e8d1f…
MD590df58834045…
PURLpkg:agent-skill/peytoncasper/browser@1.0.1
Size28.4 KB
What does this skill actually do?
Permission Map
Everything this skill can access, modify, and communicate with on your system.
Reads from
Reads setup.json to determine whether installation is completeReads browser pages and their contents through the browser CLIUses a persistent Chrome profile at .chrome-profile/ that may contain cookies and saved session data
Writes to
Writes screenshots to ./agent/browser_screenshots/Writes downloaded files to ./agent/downloads/Writes browser profile data to .chrome-profile/Instructs the user/agent to update setup.json after installation
Runs
Runs npm install to install dependenciesRuns npm link to create a global browser commandRuns browser CLI commands such as navigate, act, extract, observe, screenshot, and close
Talks to
Permissions Requested
Reads files on your machineCreates and modifies filesSends data to external serversRuns commands on your systemModifies your agent's settingsAccesses other agent sessionsWrites to your workspace filesRuns code on agent eventsCreates child agentsChanges available tools
Network Calls
https://example.com/product/123https://example.com/contacthttps://techcrunch.comhttps://example.com/loginhttps://example.com/dashboardhttps://www.google.comhttps://example.com/documents/report.pdfhttps://example.com/formhttps://example.com/productshttps://example.comhttps://www.google.com/chrome/http://localhost:9222/json/versionhttps://clawhub.ai/user/peytoncasperhttps://clawhub.ai/peytoncasper/skills/browser-automation
File Writes
.chrome-profile/./agent/browser_screenshots/./agent/downloads/setup.json