Skip to content
← Registry
Trust Report

gemini-research-browser-use

Use Chrome DevTools Protocol to allow the AI to "ask Gemini" or "research with Gemini" directly. This uses the user's logged-in Chrome session, bypassing API limits and leveraging the web interface's reasoning capabilities.

45
REJECTED
Format: openclawScanner: v0.7.1Duration: 30msScanned: 7d ago · Apr 1, 12:28 PMSource →
Embed this badge
AgentVerus REJECTED 45AgentVerus REJECTED 45AgentVerus REJECTED 45
[![AgentVerus](https://agentverus.ai/api/v1/skill/0483e918-9520-401f-a13b-764042ce5670/badge)](https://agentverus.ai/skill/0483e918-9520-401f-a13b-764042ce5670)
Community Discussion

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.

0 comments

Sign in to comment on this skill

No comments yet. Be the first to share your thoughts.

Continue the workflow

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/0483e918-9520-401f-a13b-764042ce5670/trust
Personalized next commands

Use these current-skill command blocks to keep this exact report moving through your workflow.

Record an interaction
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":"0483e918-9520-401f-a13b-764042ce5670","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'
Fetch trust JSON
curl https://agentverus.ai/api/v1/skill/0483e918-9520-401f-a13b-764042ce5670/trust

Category Scores

37
Permissions
100
Injection
38
Dependencies
40
Behavioral
60
Content
100
Code Safety

Findings (15)

criticalDownload-and-execute pattern detected-25

The skill contains instructions to download and execute external code, which is a severe supply chain risk.

curl -s http://localhost:9222/json | python

Never download and execute external code. Bundle all required functionality within the skill.

dependenciesASST-04
highCapability contract mismatch: inferred credential access is not declared-15

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.

Content pattern: remote-debugging-port

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-05
highCapability contract mismatch: inferred command execution is not declared-12

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.

Content pattern: subprocess

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
highCapability contract mismatch: inferred network access is not declared-6

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.

Content pattern: https://gemini.google.com/

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-04
highCapability contract mismatch: inferred local service access is not declared-10

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.

Content pattern: http://localhost:9222

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
highCapability contract mismatch: inferred local input control is not declared-8

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.

Content pattern: insertText

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
highLocal file access detected (inside code block)-15

Found local file access pattern: "`gemini_query.py`"

Save this as `gemini_query.py` or run inline:

Treat local file browsing as privileged access. Restrict it to explicit user-approved paths and avoid combining it with unrestricted browser/session reuse.

behavioralASST-03
highHigh-risk workflow lacks explicit safety boundaries-20

The skill performs or enables higher-risk operations but does not define explicit safety boundaries describing what it must not do.

No safety boundary patterns found alongside high-risk capability language

Add a 'Safety Boundaries' section listing what the skill must NOT do (e.g., no file deletion, no network access beyond needed APIs).

contentASST-09
highMany external URLs referenced (4)-8

The skill references 4 external URLs and also discusses auth/API/payment workflows, which increases the chance that sensitive operations depend on many remote endpoints.

URLs: https://gemini.google.com/`, http://localhost:9222/json, https://gemini.google.com/, https://gemini.google.com/app

Minimize external dependencies to reduce supply chain risk.

dependenciesASST-04
highCapability contract mismatch: inferred browser session attachment is not declared-12

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.

Content pattern: remote-debugging-port

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
highBrowser session attachment detected-15

Found browser session attachment pattern: "Chrome DevTools" Related auth/profile context: - overlapping signals from the same local context — External AI provider delegation detected

description: Use Chrome DevTools Protocol to allow the AI to "ask Gemini" or "research with Gemini" directly. This uses the user's logged-in Chrome session, bypassing API limits and leveraging the web

Treat browser profile reuse, remote-debugging attachment, and live-session access as sensitive credential access. Require explicit user consent, minimize scope, and clean up persisted state.

behavioralASST-05
highLocal service URL reference-8

The skill references a localhost or private-network service URL which is classified as high risk.

http://localhost:9222/json

Review localhost/private-network service references carefully. Local service URLs can expose internal apps, admin panels, or developer tooling to agent-driven workflows.

dependenciesASST-04
highLocal service access detected-15

Found local service access pattern: "http://localhost:9222"

curl -s http://localhost:9222/json | python3 -m json.tool

Treat localhost and loopback services as privileged local attack surfaces. Require explicit approval, constrain reachable ports, and avoid combining local access with session reuse or tunneling.

behavioralASST-03
mediumUnknown external reference-8

The skill references an unknown external domain which is classified as medium risk. Merged overlapping signals from the repeated finding family: - Unknown external reference

https://gemini.google.com/`

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowUnknown external reference-5

The skill references an unknown external domain which is classified as low risk.

https://gemini.google.com/app

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04