Skills/ClawHub/mli-paper-reading

mli-paper-reading@0.1.1

CAUTION· static only

Publisher claims: "Academic paper reading and literature research skill for paper-reading, 论文阅读, 论文精读, 文献阅读, literature review, arXiv, DOI, PDF, paper title, or paper list task..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher pengheliu · publishing for 137 daysInstalls 555Last detonated 2d 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 2026-11-12 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Privileged sudo command; Privileged sudo command. 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

HIGH
Privileged sudo commandSKILL.md:166 · Privileged sudo command — agent may execute with elevated privileges| **lsof** | 端口检测（Step 3） | macOS 内置；Linux: `sudo apt install lsof` | 不可用时直接用 7410 端口 |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:390 · Process kill command — agent can terminate processes停止服务：kill $(cat /tmp/paper-notes-server.pid)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedSKILL.md:140 · Python subprocess execution detectedr = subprocess.run(["curl", "--version"], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandSKILL.md:168 · Privileged sudo command — agent may execute with elevated privileges| **open** / **xdg-open** | 打开浏览器（Step 4） | macOS 内置；Linux: `sudo apt install xdg-utils` | 不可用时打印 URL 请用户手动打开 |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedSKILL.md:147 · Python subprocess execution detectedr = subprocess.run(["which", "xdg-open"], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandSKILL.md:167 · Privileged sudo command — agent may execute with elevated privileges| **curl** | 服务健康检查（Step 3） | macOS 内置；Linux: `sudo apt install curl` | 不可用时改 `sleep 1` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:163 · Privileged sudo command — agent may execute with elevated privileges| **Python 3.7+** | 所有步骤 | macOS 内置；Linux: `sudo apt install python3` | `http.server --directory` 需 3.7+ |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedSKILL.md:137 · Python subprocess execution detectedr = subprocess.run(["lsof", "-h"], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈3,426 tok
1 file · 2 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

21 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim pengheliu: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pengheliuPropose a patch to the maintainer