one-novel-skill@1.0.0
CAUTION· static onlyPublisher claims: "融合级中文小说创作。从零开书到长篇日更,四层反AI防护,12套L2检测,创作宪法/澄清决策/时间线校验,多视角对抗式审查。你说'帮我写个小说',剩下的我来做。零配置自适应LLM,支持Ollama任意模型/OpenClaw/DeepSeek/OpenAI/Claude/Gemini/通义千问/智谱/月之暗面/百川/自定义端点,安装即用。" Observed in sandbox: static analysis only — behavior not yet observed.
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 2026-11-12 and scored it 65/100 (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 onlyThis 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
"pacing": "\u5feb\u8282\u594f\uff0c\u6bcf\u7ae0\u6709\u5c0f\u51b2\u7a81\uff0c\u5f00\u7bc7\u5373\u77db\u76fe",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."reader": "\u91cd\u5ea6\u9605\u8bfb\u8005\uff0c\u5bf9\u8bbe\u5b9a\u4e25\u8c28\u6027\u8981\u6c42\u9ad8",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.result = subprocess.run(cmd, capture_output=True, text=True, timeout=15)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.lines.append("\u3010\u524d\u60c5\u63d0\u8981\u3011")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._log.info("PhaseGate: \u516d\u5927\u5e93\u5168\u90e8\u5c31\u7eea\uff0c\u53ef\u4ee5\u5f00\u59cb\u5199\u4f5c")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."pacing": "\u4e2d\u6162\u901f\u85c4\u529b\uff0c\u9ad8\u6f6e\u91ca\u653e\u5145\u5206",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.lines.append("\u3010\u672a\u56de\u6536\u4f0f\u7b14\u3011")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."opening": "\u524d50\u7ae0\u5efa\u7acb\u5b8c\u6574\u529b\u91cf\u4f53\u7cfb\u548c\u4e3b\u7ebf\u76ee\u6807\uff0c\u53ef\u94fa\u57ab\u8f83\u957f",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.lines.append("\u3010\u89d2\u8272\u72b6\u6001\u3011")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.lines.append("\u3010\u76f8\u5173\u89d2\u8272\u3011")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.status.messages.append("ResearchEngine: \u26a0\ufe0f \u7814\u7a76\u5f15\u64ce\u672a\u914d\u7f6e\u5b8c\u5584")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.status.messages.append("ResearchEngine: \u2705 \u7814\u7a76\u5f15\u64ce\u5c31\u7eea")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.lines.append("\u3010\u6d3b\u8dc3\u4f0f\u7b14\u3011")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._log.warning(f"PhaseGate: \u7981\u6b62\u5f00\u59cb\u2014\u2014\u516d\u5927\u5e93\u672a\u5168\u90e8\u5c31\u7eea")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."taboo": "\u8fc7\u5ea6\u73a9\u689f/\u6c99\u96d5\u98ce\u3001\u903b\u8f91\u5d29\u574f",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.# --- Phase C3b-ii: WorldEngine — 世\u754c\u89c2\u89c4\u5219\u6821\u9a8c ---Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."paragraph": "\u6bb5\u843d\u63a7\u5236\u57281-3\u53e5\uff0c\u5bf9\u8bdd\u5360\u6bd430-50%",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._log.warning(f"Pipeline: ch{ch} \u5168\u5c40\u8bb0\u5fc6\u5f15\u64ce\u5931\u8d25: {_gme}")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."opening": "\u524d300\u5b57\u5fc5\u987b\u5b8c\u6210\uff1a\u4ecb\u7ecd\u4e3b\u89d2 + \u7ed9\u91d1\u624b\u6307/\u7cfb\u7edf + \u7b2c\u4e00\u4e2a\u51b2\u7a81",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.status.messages.append(f"ReferenceEngine: \u2705 \u53c2\u8003\u6587\u6863\u5c31\u7eea ({len(ref_files)}\u4e2a)")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."pacing": "\u6781\u5feb\u8282\u594f\uff0c\u6bcf\u7ae0\u81f3\u5c111\u6b21\u60c5\u7eea\u6ce2\u52a8",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._log.debug("Pipeline: ch{} \u4e16\u754c\u89c2\u5f15\u64ce\u5931\u8d25: {}".format(ch, _we_e))Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."ending": "\u7ae0\u672b\u5fc5\u987b\u65ad\u5728\'\u63a5\u4e0b\u6765\u4f1a\u600e\u6837\'\u7684\u60ac\u5ff5\u4e0a",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.Cost to the agent
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
15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim xincen0725: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.