agent-browser
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
[](https://agentverus.ai/skill/cb878d42-608f-42ac-8180-774f16adcfba)Community Comments
Public comments are the active feedback surface on skill reports right now. Use them to share implementation notes, edge cases, and operator context.
Sign in to comment on this skill
No comments yet. Be the first to share your thoughts.
Keep this report moving through the activation path: rescan from the submit flow, capture real-world interactions, and wire the trust endpoint into your automation.
https://agentverus.ai/api/v1/skill/cb878d42-608f-42ac-8180-774f16adcfba/trustUse your saved key to act on this report immediately instead of returning to onboarding.
Use these current-skill command blocks to keep this exact report moving through your workflow.
curl -X POST https://agentverus.ai/api/v1/interactions \
-H "Authorization: Bearer at_your_api_key" \
-H "Content-Type: application/json" \
-d '{"agentPlatform":"openclaw","skillId":"cb878d42-608f-42ac-8180-774f16adcfba","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'curl https://agentverus.ai/api/v1/skill/cb878d42-608f-42ac-8180-774f16adcfba/trustCategory Scores
Findings (23)
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The skill instructs users to download and execute code from a remote URL, a common supply-chain attack vector.
→ Remove curl-pipe-to-shell patterns. Provide dependencies through safe, verifiable channels.
Piping a downloaded script directly to a shell interpreter. This executes remote code without verification — a classic supply chain attack vector.
→ Review the code block starting at line 15. Ensure this pattern is necessary and does not pose a security risk.
Found remote browser delegation pattern: "Proxy Support"
→ Treat cloud or remote browser execution as external data egress. Be explicit about what page content, cookies, or secrets may leave the local machine, and require user approval before delegating authenticated sessions.
Found ui state enumeration pattern: "Re-snapshot" Merged overlapping signals from the repeated finding family: - UI state enumeration detected
→ Treat DOM/accessibility snapshots and clickable-element inventories as sensitive page-state extraction. Be explicit about when UI enumeration is allowed, especially on authenticated or local-only apps.
Found browser content extraction pattern: "data extraction" Merged overlapping signals from the repeated finding family: - Browser content extraction detected
→ Treat browser page capture and HTML/text extraction as potential data-access operations, especially when sessions may be authenticated. Make the data-access scope explicit and avoid collecting more page content than needed.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The skill depends on a hosted or proxy-backed browser service, which introduces an external execution surface and additional dependency trust requirements.
→ Review which external services or providers the skill depends on, what data crosses that boundary, and whether the dependency is necessary for the intended workflow.
The skill contains a download-and-execute pattern inside a code block. Verify the URL is trustworthy.
→ Pin the installer to a specific version or hash. Consider bundling dependencies instead.
The skill references 11 external URLs and also discusses auth/API/payment workflows, which increases the chance that sensitive operations depend on many remote endpoints.
→ Minimize external dependencies to reduce supply chain risk.
Found federated auth flow pattern: "OAuth" Related auth/profile context: - overlapping signals from the same local context — Federated auth flow detected
→ Treat OAuth, 2FA, and token-refresh guidance as authentication-sensitive workflows. Explain scope, storage, and refresh behavior clearly so agents do not handle more credential material than necessary.
The skill references an unknown external domain which is classified as medium risk. Merged overlapping signals from the repeated finding family: - Unknown external reference
→ Verify that this external dependency is trustworthy and necessary.
Found package bootstrap execution pattern: "npx skills"
→ Surface package bootstrap commands for review. Ephemeral package execution and install-time dependency pulls increase supply-chain risk, especially when versions are not pinned or provenance is unclear.
The skill references an unknown external domain which is classified as low risk.
→ Verify that this external dependency is trustworthy and necessary.
The skill references an unknown external domain which is classified as low risk.
→ Verify that this external dependency is trustworthy and necessary.
The skill does not include explicit safety boundaries defining what it should NOT do.
→ Add a 'Safety Boundaries' section listing what the skill must NOT do (e.g., no file deletion, no network access beyond needed APIs).