Skills/ClawHub/critical-thinking

critical-thinking@1.2.1

VERIFIED

Publisher claims: "On-demand direction check. Pressure-tests a plan, decision, premise, or requested approach before effort goes into it — separates the real goal from the chosen method, tests the assumptions, weighs alternatives and the cost of being wrong, then gives a clear verdict and the cheapest test. Read-only; never edits files or agent instructions." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher srmhrrm-hub · joined 0 days agoInstalls 206Last detonated 1 h ago
$clawhub install critical-thinking
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-26 and scored it 82/100 (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

MEDIUM
Process kill commandSKILL.md:55 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:71 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01