Skills/ClawHub/chrome-extension-installer

chrome-extension-installer@1.0.0

CAUTION· static only

Publisher claims: "Install a Chrome extension by ID or Chrome Web Store URL on this Mac." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher ryanpwelliver-oss · publishing for 157 daysInstalls 562Last detonated 23 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-13 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection; Privileged sudo command; Authorization escalation language. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

CRITICAL
Prompt injectionSKILL.md:39 · Prompt injection — known jailbreak technique reference- From installed extension: chrome://extensions → enable Developer Mode → ID shown under each extensionFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Privileged sudo commandSKILL.md:51 · Privileged sudo command — agent may execute with elevated privileges- Method 2 requires sudo and persists across Chrome updates.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageSKILL.md:39 · Authorization escalation language- From installed extension: chrome://extensions → enable Developer Mode → ID shown under each extensionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Context shift attemptSKILL.md:39 · Context shift attempt — trying to change operational mode- From installed extension: chrome://extensions → enable Developer Mode → ID shown under each extensionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandSKILL.md:27 · Privileged sudo command — agent may execute with elevated privilegessudo defaults write "$PLIST" ExtensionInstallForcelist -array-add "$EXTENSION_ID;https://clients2.google.com/service/update2/crx"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈475 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.

What would make this Verified

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim ryanpwelliver-oss: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ryanpwelliver-ossPropose a patch to the maintainer