Skills/ClawHub/skill-collision-guard

skill-collision-guard@0.1.1

VERIFIED

Publisher claims: "Use only when the user explicitly asks to inspect or compare coding-agent skills before installation or invocation. The workflow uses bounded local discovery, optional read-only Git candidate retrieval, deterministic comparison of names, capabilities, policies, and behavior, and reversible session suppression; it reads SKILL.md files only, never executes candidate code or installs/removes skills, and leaves conflict decisions with the user." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher three-liu · joined 2 days agoInstalls 415Last detonated 2d ago
$clawhub install skill-collision-guard
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-30 and scored it 84/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. 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

Static findings

CRITICAL
Agent configured for autonomous execution without human approvalsrc/analyzer.js:25 · Agent configured for autonomous execution without human approvalFix: Declare and request only the permissions the task needs.
AST02

No other findings across 1,586 lines in 13 files.

skill-collision-guard@0.1.1 safety verdict: Verified 84/100 — KillerSkills