Skills/npm/promptfigure

promptfigure@0.3.2

CAUTION

Publisher claims: "promptFigure 本地插件：在你的 AI 宿主（Codex / Claude Code 等）里为论文配科研图。开文档（LaTeX 本地编译）、画锚点、本地规则层组装提示词、调出图、收审批。npm 安装即附带 promptfigure-local / promptfigure-api 两个 Agent Skill。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry npm (MCP server)Publisher zhangmask · joined 7 days agoInstalls 60Last detonated 7d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-27 and scored it 45/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Outbound HTTP to raw IP address; Host or command assembled from base64 fragments; Outbound HTTP to raw IP address. 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
Outbound HTTP to raw IP addressbin/pf.mjs:1935 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Host or command assembled from base64 fragmentsadapters/codex/promptfigure/skills/promptfigure-api/SKILL.md:171 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Outbound HTTP to raw IP addressbin/pf.mjs:549 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Host or command assembled from base64 fragmentsadapters/claude-code/promptfigure-api/SKILL.md:171 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
URL with suspicious TLDadapters/claude-code/promptfigure-api/SKILL.md:11 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDadapters/claude-code/promptfigure-api/SKILL.md:9 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDadapters/codex/promptfigure/skills/promptfigure-api/SKILL.md:3 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDadapters/codex/promptfigure/skills/promptfigure-api/SKILL.md:9 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDadapters/claude-code/promptfigure-api/SKILL.md:18 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDadapters/claude-code/promptfigure-api/SKILL.md:3 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addresssrc/server.mjs:57 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Host or command assembled from base64 fragmentsskill/promptfigure-api/SKILL.md:171 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Outbound HTTP to raw IP addressscripts/test-e2e.mjs:94 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addresstray/pf-tray.py:115 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDadapters/claude-code/promptfigure-api/SKILL.md:162 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDadapters/codex/promptfigure/skills/promptfigure-api/SKILL.md:162 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandbin/pf.mjs:1947 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL using raw IP addressscripts/test-e2e.mjs:94 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDbin/pf.mjs:446 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDadapters/codex/promptfigure/skills/promptfigure-api/SKILL.md:18 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDadapters/codex/promptfigure/skills/promptfigure-api/SKILL.md:11 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDskill/promptfigure-api/SKILL.md:3 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addressbin/pf.mjs:1935 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandbin/pf.mjs:1961 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL with suspicious TLDbin/pf.mjs:493 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addressbin/pf.mjs:549 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDskill/promptfigure-api/SKILL.md:9 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtray/pf-tray.py:96 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL with suspicious TLDskill/promptfigure-api/SKILL.md:11 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtray/pf-tray.py:134 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL with suspicious TLDskill/promptfigure-api/SKILL.md:18 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addresstray/pf-tray.py:115 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDsrc/render.mjs:17 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDskill/promptfigure-api/SKILL.md:162 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtray/pf-tray.py:229 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtray/pf-tray.py:146 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using raw IP addresssrc/server.mjs:57 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

What would make this Verified

35 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim zhangmask: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
  3. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  4. Host or command assembled from base64 fragments≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  5. URL with suspicious TLD≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim zhangmask