Skills/ClawHub/openclaw-auto-research

openclaw-auto-research@1.0.0

CAUTION· static only

Publisher claims: "OpenClaw 原生的自动化研究 pipeline。从一个研究 topic 出发，经过 23 个 stage 产出完整论文。 每个 Phase 由独立 sub-agent 执行（context 隔离），Phase 间通过文件系统传递产出。 触发词：Research X、跑研究、文献调研、写论文、研究 pipel..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher lixiang1076 · publishing for 233 daysInstalls 902Last detonated 19 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 2026-11-15 and scored it 70/100 (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
Prompt injection attemptreferences/phase-b-literature.md:73 · Prompt injection attempt — fake system prompt · informational: not an instruction fileSystem: You are a literature search assistant with knowledge up to 2025.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/phase-h-finalize.md:129 · Prompt injection attempt — fake system prompt · informational: not an instruction fileSystem: You are a LaTeX formatting expert.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/phase-h-finalize.md:144 · Prompt injection attempt — fake system prompt · informational: not an instruction fileSystem: You are a bibliographer.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/domains.yaml:196 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- jailbreakFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/phase-a-scoping.md:61 · Prompt injection attempt — fake system prompt · informational: not an instruction fileSystem: You are a research topic evaluator.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/phase-h-finalize.md:188 · Prompt injection attempt — fake system prompt · informational: not an instruction fileSystem: You are a citation fact-checker.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈1,786 tok
1 file · 13 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

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim lixiang1076: 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 lixiang1076Propose a patch to the maintainer