Skills/ClawHub/qrcode-skills

qrcode-skills@1.0.1

CAUTION· static only

Publisher claims: "Generate and decode QR codes locally. Use when the user wants to create a QR code from text/URL, decode/read QR code content from an image, or asks about QR..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher hinisal · publishing for 253 daysInstalls 1,334Last detonated 26 min ago

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 2026-11-20 and scored it 66/100 (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

MEDIUM
File type combined with upload actionscripts/batch_decode.js:212 · File type combined with upload action — agent may exfiltrate local data fileselse if (ext === ".csv") result = await processCsv(args.input, args.column, args.outputTxt);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:14 · npx invocation of non-well-known package — may execute untrusted code如需二维码生成 URL(无需保存文件即可预览)、更好的解码效果,可使用 [qrcode-remote-skills](https://github.com/caoliao/qrcode-remote-skills):`npx skills add caoliao/qrcode-remote-skills`。Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/batch_decode.js:207 · File type combined with upload action — agent may exfiltrate local data filesif (!args.input) { console.log(JSON.stringify({ error: "用法: node batch_decode.js --input <文件> [选项]" })); process.exit(1); }Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/generate.js:34 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify({ error: "用法: node generate.js --data <文本> --output <路径>" }));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/batch_generate.js:128 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify({ error: "必须指定 --output-dir" }));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/generate.js:54 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify({ file: outputPath }));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/batch_generate.js:184 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify({ error: "用法: node batch_generate.js --input <文件> --output-dir <目录> [选项]" }));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/batch_decode.js:211 · File type combined with upload action — agent may exfiltrate local data filesif (ext === ".txt") result = await processTxt(args.input, args.outputTxt);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,686 tok
1 file · 14 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

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim hinisal: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim hinisalPropose a patch to the maintainer