Skills/ClawHub/chrome-remote-browser

chrome-remote-browser@1.0.0

VERIFIED· install only

Publisher claims: "Guide for AI agents on how to use Chrome Remote Debugging (CDP on port 9222) to automate browser interactions. Covers the full lifecycle — connecting, naviga..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher lgx-00 · publishing for 233 daysInstalls 822Last detonated 2 h ago
$clawhub install chrome-remote-browser
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

CRITICAL
Rule modification attemptSKILL.md:311 · Rule modification attempt — overwriting existing instructions### Rule 5: Handle Google Account SwitchingFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:285 · Rule modification attempt — overwriting existing instructions### Rule 2: ALWAYS Screenshot After State ChangesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:301 · Rule modification attempt — overwriting existing instructions### Rule 4: Handle Page Load DelaysFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:276 · Rule modification attempt — overwriting existing instructions### Rule 1: ALWAYS Snapshot Before ActingFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:293 · Rule modification attempt — overwriting existing instructions### Rule 3: Re-snapshot After EVERY Page ChangeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈3,737 tok
1 file · 2 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

chrome-remote-browser@1.0.0 safety verdict: Verified (install only) — KillerSkills