Skills/ClawHub/skill-cybernetic-thinking

skill-cybernetic-thinking@0.6.0

CAUTION· static only

Publisher claims: "Thinking-mode skill for LLMs: installs a control-theoretic and systems-theoretic cognitive operating system distilled from two books — Tsien Hsue-shen & Song Jian's "Engineering Cybernetics" (工程控制论) and Jin Guantao's "Cybernetics and Scientific Methodology" (控制论与科学方法论). Shapes how the LLM reasons about systems, not just how it writes patch diffs. Teaches the model to identify state and possibility space, model the plant as a black-box hypothesis, demand observability and information channels, verify stability and convergence, respect bounds, decouple harm, coordinate benefits, recognize ultra-stability and bifurcations, and close the loop before declaring success. Use when designing architecture, writing complex code, refactoring coupled modules, debugging non-deterministic systems, or any task where "correct AND robust" cannot be verified by a single happy path." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher shrimpleon · publishing for 97 daysInstalls 761Last detonated 5d ago
What would fix thisWatchDispute verdict

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 2026-11-09 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. 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

LOW
Authorization escalation languageCHANGELOG.md:57 · Authorization escalation language · informational: not an instruction file- Windows symlinks use `junction` (no admin rights needed for directory junctions); real symlinks may still require Developer Mode or admin on some setupsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Refusal suppressionreferences/possibility-space.md:113 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file- Do not refuse to act because the model is incomplete. Use feedback to *build* the modelFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagescripts/install.js:177 · npx invocation of non-well-known package — may execute untrusted codeconsole.log(`Usage: npx ${skillName} install [options]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandSKILL.md:95 · Process kill command — agent can terminate processes3. **Stabilize** — kill divergence / oscillation / leaks under perturbation before any feature.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/install.js:199 · npx invocation of non-well-known package — may execute untrusted codenpx ${skillName} install -a claude,codex,workbuddyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.js:6 · npx invocation of non-well-known package — may execute untrusted code* UX mirrors `npx impeccable skills install` using @clack/prompts:Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.js:200 · npx invocation of non-well-known package — may execute untrusted codenpx ${skillName} install --path ~/my-agent/skillsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.js:198 · npx invocation of non-well-known package — may execute untrusted codenpx ${skillName} installFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionCHANGELOG.md:57 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- Windows symlinks use `junction` (no admin rights needed for directory junctions); real symlinks may still require Developer Mode or admin on some setupsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈2,528 tok
1 file · 26 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

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim shrimpleon: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Process kill command≈ +2 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 shrimpleonPropose a patch to the maintainer