paper-polisher-pro@7.8.0
CAUTION· static onlyPublisher claims: "AI-rate self-check and polish guidance for academic writing: sentence-level rewrite suggestions (locates and advises, never auto-rewrites), terminology and consistency checks, translation-smell, paragraph attribution, journal precheck with discipline context, style-norm conventions check, quality report, AIGC label check, plus `--batch DIR` with HTML summary. Reads .docx directly. Not for: document/PDF translation (doc-holmes), plagiarism checking (institutional systems), ghost-writing or executing rewrites (paper-rewriter); texts under 100 chars get no verdict by design. 100% local, zero upload; bundled tests + AST zero-network self-verification. Multi-layer rule engine + token spectrum + optional supervised Qwen3-0.6B ONNX layer (held-out AUROC 0.9998, fingerprint-bound) + LLM fingerprint attribution + freshness pipeline. Base-engine numbers reproduce from bundled held-out evals; supervised columns are author-side (model not bundled)." 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.
What changed since 7.7.0
vet-skills diff paper-polisher-pro 7.7.0 7.8.0In the sandbox, this version reached for nothing 7.7.0 did not. Compared from the two recorded runs, not from source.
7.7.0 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 63/100 (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
_pp_d = subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "detect", _route_f,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._pp = subprocess.run([sys.executable, str(SCRIPTS / "pp.py")],Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._pp_bad = subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "no-such-cmd"],Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._dfr = subprocess.run([sys.executable, str(_df), "--root", str(ROOT)],Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._p = subprocess.run([sys.executable, str(SCRIPTS / "ai_detector.py"), _hu_file_hold,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._gc = subprocess.run([sys.executable, str(_gen), "--check"],Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.p = subprocess.run([sys.executable, str(SCRIPTS / script)] + args,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.p = subprocess.run([sys.executable, str(SCRIPTS / "ai_detector.py"), empty_f, "--format", "json"],Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._p2 = subprocess.run([sys.executable, str(SCRIPTS / "pp_setup.py"), "--model", str(_fake)],Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._p = subprocess.run([sys.executable, str(SCRIPTS / "pp_setup.py"), "--check"],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([py, ev, "--corpus", a.corpus, "--split", "test",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out._ppu = subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "no-such"], capture_output=True,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(cmd, capture_output=True, text=True, encoding="utf-8", errors="ignore",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(Path(__file__).resolve()),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, str(HERE / "pp_explain.py"), str(wf)], timeout=180)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(copy / "eval" / "release_smoke.py"), "--fast"],Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.out = subprocess.run([sys.executable, PP, "quickstart"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_fix_suggest.py"), "--demo"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, str(HERE / "ai_detector.py"), demo], timeout=180)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out._ppe = subprocess.run([sys.executable, str(SCRIPTS / "pp.py")], capture_output=True,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.out = subprocess.run([sys.executable, str(SCRIPTS / "ai_detector.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, PP, "no-such-cmd"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_batch_report.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_fix_suggest.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable] + args, capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_fix_suggest.py"), p],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / script)] + args,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_report_bundle.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(copy / "eval" / "release_smoke.py"),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.subprocess.run([sys.executable, str(HERE / "pp_doctor.py")], timeout=180)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "ai_detector.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([sys.executable, str(HERE / "pp_schema.py")] + args[1:]).returncodeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, "-c", code],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out._ut = subprocess.run([sys.executable, "-m", "unittest", "discover", "-s", "tests",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.subprocess.run([sys.executable, str(HERE / "pp_fix_suggest.py"), demo, "--top", "3"], timeout=180)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, str(HERE / "ai_detector.py"), demo], timeout=180)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, PP], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, str(HERE / "pp_doctor.py")], timeout=180)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / script)] + args,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(HERE / script)] + args[1:])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, str(HERE / "pp_fix_suggest.py"), demo, "--top", "3"], timeout=180)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_batch_report.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, str(HERE / "paragraph_report.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(HERE / "ai_detector.py"), str(path),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "freshness_refresh.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "term_check.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_doctor.py"), "--deep"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(PKG / "eval" / "gen_integrity_manifest.py")],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([PY, *map(str, args)], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "tour"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_project.py"), str(d)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "scenarios", "项目"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp.py")],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_fix_suggest.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "term_check.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_style_norm.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([sys.executable] + args, capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp.py")],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([PY, str(SCRIPTS / "pp.py"), *args],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / script), str(p)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "recommend", "功能太多不知从哪开始"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SERVER)], input="\n".join(lines),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_term_consistency.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([PY, *map(str, args)], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_project.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.cls.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_rewrite_check.py"), "--demo"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp.py")],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "ai_detector.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_project.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([sys.executable] + args, capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([PY, *map(str, args)], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r2 = subprocess.run([sys.executable, str(SCRIPTS / "pp_doctor.py"), "--deep"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([PY, str(SCRIPTS / "pp_report_html.py"), str(evil),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_rewrite_check.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([PY, *map(str, args)], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "tour"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([PY, *map(str, args)], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_fix_suggest.py"),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.p = subprocess.run([sys.executable, str(SCRIPTS / "ai_detector.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([PY, str(SCRIPTS / "pp_report_html.py"), str(junk),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_mcp_server.py")],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r_en = subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "scenarios"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "recommend", "全稿自查项目"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "ai_detector.py"), "--help"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SERVER)], input="{broken",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.bad = subprocess.run([sys.executable, str(SCRIPTS / "pp_rewrite_check.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_doctor.py"), "--deep"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…_suggest / workflow / term_report) ship JSON-Schema contracts (`schemas/*.schema.json`, draft-2020-12 subset). Self-check: `python3 scripts/pp.py schema --selfcheck` runs real engine outputs against every contract — contract/implementation…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_verify.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.nγδFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LS = importlib.util.module_from_spec(spec); spec.loader.exec_module(LS)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own._raw = (ZH_HUMAN[:40] + "\ufffd\ufffd\ufffd\ufffd\ufffd\ufffd\ufffd\ufffd") * 6Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.python3 scripts/pp_mcp_server.py --transport http --port 8815 # 本地 HTTP(v7.2.0)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.nγδFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| batch mode (--batch) | .txt/.md/.docx <5 MB per file | >5 MB skipped by design; encrypted/image-only docx yield an explicit error, not silent empty output |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.nγδFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.p = subprocess.run([sys.executable, str(PKG / "eval" / "gen_integrity_manifest.py"), "--check"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "pp_schema.py"), "--selfcheck"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "freshness_refresh.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([sys.executable, str(SCRIPTS / "pp.py"), "detect",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(SCRIPTS / "freshness_refresh.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([sys.executable, str(PKG / "eval" / "doc_facts.py"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…y policy. - **v7.7.0 (2026-11-12)** — output contract schemas (`schemas/*.schema.json` + zero-dep validator `pp.py schema --selfcheck`, real-output-validated); manifest generator single-sourced (generated reads skill.json, --ch…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…script paths. Local HTTP form (v7.2.0, multi-client reuse): `python scripts/pp_mcp_server.py --transport http --port 8815` — listens on 127.0.0.1 loopback only (consistent with the zero-net…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.out = subprocess.run([sys.executable, str(SCRIPTS / "pp_verify.py"), "--json"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.if a.json and not a.output:Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.p = subprocess.run([sys.executable, str(SCRIPTS / "pp.py")],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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
17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim docsor1212: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Python subprocess execution 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.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- 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.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
- Dynamic module loading≈ +1 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.