Skills/ClawHub/browser-harness-skill

browser-harness-skill@1.0.5

VERIFIED· install only

Publisher claims: "用 LLM 友好的方式控制用户已登录的真实 Chrome(CDP)。一行命令在当前标签页跑 JS、点击、滚动、截图、读 DOM、填表、上传文件——共享 cookie/session/登录态,跨 Python 与 TypeScript Agent 操作同一个浏览器。基于 browser-use/browser-ha..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher sipingme · publishing for 245 daysInstalls 1,130Last detonated 15 h ago
$clawhub install browser-harness-skill
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
2 of 2 bundled scripts run with no arguments, with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 81/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexec /usr/bin/dirname
0.0sprocessexec /usr/bin/cat
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: browser-harness skill: 缺少子命令
0.1sprocess2 of 2 bundled scripts run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

CRITICAL
Pipe-to-shell patternscripts/run.sh:120 · Pipe-to-shell pattern — downloads and immediately executes remote codeprintf " curl -LsSf https://astral.sh/uv/install.sh | sh\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandscripts/run.sh:340 · File permission modification command — agent changes file ownership/permissionschmod 0600 "$AUDIT_LOG" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionscripts/lib/runner.mjs:424 · File type combined with upload action — agent may exfiltrate local data filesconsole.log("uploaded", ${lit(path)}, "->", ${lit(selector)});Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Remote installer piped to shellscripts/run.sh:120 · Remote installer piped to shellprintf " curl -LsSf https://astral.sh/uv/install.sh | sh\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File permission modification commandscripts/run.sh:282 · File permission modification command — agent changes file ownership/permissionschmod 0600 "$AUDIT_LOG" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈2,551 tok
1 file · 9 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.