Skills/ClawHub/attacker

attacker@0.8.2

VERIFIED

Publisher claims: "Attack any target (skill, design, argument, code, KB) with a FRESH independent attacker rotating five lenses; coverage-first strike, then PROVE-OR-FLAG adjudication (findings vs flags); never fixes. A different-vendor attacker buys stronger independence. Use-when: "red-team/break this", "$attacker". Do-NOT: fix or edit the target." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher vincentjiang06 · joined 1 days agoInstalls 1,026Last detonated 20 h ago
$clawhub install attacker
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 93/100 (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
Rule addition attemptCHANGELOG.md:333 · Rule addition attempt — injecting new instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 1,580 lines in 15 files.