Skills/ClawHub/paper-results-reverse-engineer

paper-results-reverse-engineer@3.0.4

CAUTION· static only

Publisher claims: "心理学论文 Results 反向拆解技能 v3.0.4 稳定版。采用三轴分类（文章类型 × 领域 × 数据模态）、研究画像优先工作流、A–I 九分支自适应架构，覆盖实验、问卷、RCT、心理测量、元分析、神经影像坐标元分析、质性研究（主题分析、IPA、扎根理论、建构主义扎根理论）及方法学模拟等各类研究设计。默认输出..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher bin77-chris · publishing for 173 daysInstalls 862Last detonated 30 min 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 2026-11-14 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Rule modification attempt; Rule modification attempt; Rule modification attempt. 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
Rule modification attemptSKILL.md:154 · Rule modification attempt — overwriting existing instructions#### Rule 5: Sham-Control Trial Type DistinctionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:138 · Rule modification attempt — overwriting existing instructions#### Rule 3: Study Design TaxonomyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:142 · Rule modification attempt — overwriting existing instructions#### Rule 4: Closed-Loop Phase Precision GuardrailFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:130 · Rule modification attempt — overwriting existing instructions#### Rule 1: Day/Session Strong Evidence RuleFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Rule modification attemptdocs/branch-a-b-c-d-e-f.md:135 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 2: Diagnostic Wording GuardrailFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Rule modification attemptdocs/branch-a-b-c-d-e-f.md:126 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 1: Psychometric Evidence TaxonomyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Rule modification attemptdocs/branch-a-b-c-d-e-f.md:141 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 3: Cutoff Interpretation RuleFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:134 · Rule modification attempt — overwriting existing instructions#### Rule 2: Stimulus Pool vs Actual Task ExposureFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Rule modification attemptdocs/branch-a-b-c-d-e-f.md:145 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 4: Classic Scale Validation RuleFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)tests/test-case-6.md:35 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileΔCFIFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Rule modification attemptdocs/branch-a-b-c-d-e-f.md:149 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file### Rule 5: Psychometric Module B StructureFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈5,891 tok
1 file · 27 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

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim bin77-chris: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim bin77-chrisPropose a patch to the maintainer