Skills/ClawHub/bestcoffer-ai-redaction

bestcoffer-ai-redaction@1.0.0

CAUTION· install only

Publisher claims: "一款专为个人用户设计的智能文件脱敏工具，强调纯个人独立模式。支持通过自然语言指令，脱敏用户上传的文件，对 PDF、Word、图片等多种格式的文件进行快速、精准、安全的隐私信息处理。处理完成后返回查询链接，可查看处理进度和下载结果" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher marsxh · publishing for 162 daysInstalls 600Last detonated 11 h ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-14 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Host or code assembled from base64 fragments; Hidden zero-width characters detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/index.js:2 · File type combined with upload action — agent may exfiltrate local data files…Symbol]}}}),require_mappingTable=__commonJS({"node_modules/tr46/lib/mappingTable.json"(d,p){p.exports=[[[0,44],"disallowed_STD3_valid"],[[45,46],"valid"],[[47,47],"disallowed_STD3_valid"],[[48,57],"valid"],[[58,64],"disallowed_STD3_valid"]…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 actiondist/index.js:1 · File type combined with upload action — agent may exfiltrate local data files…reset(),this.emit("error",n)}}}),require_db=__commonJS({"node_modules/mime-db/db.json"(d,p){p.exports={"application/1d-interleaved-parityfec":{source:"iana"},"application/3gpdash-qoe-report+xml":{source:"iana",charset:"UTF-8",compressible:…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 actiondist/index.js:4 · File type combined with upload action — agent may exfiltrate local data files…r.log"),`[${i}] Failed to write ${s}: ${n} `)}catch{}}}var log={info:d=>{console.log(`[INFO] ${d}`),writeToFile("INFO",d)},error:d=>{console.error(`[ERROR] ${d}`),writeToFile("ERROR",d)},debug:d=>{console.log(`[DEBUG] ${d}`),writeToFile("D…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Host or code assembled from base64 fragmentsdist/index.js:2 · Host or code assembled from base64 fragments…e("crypto"),FIXED_IV=Buffer.from("bGlhbndlaWxpZ2UyODA2YQ==","base64"),FIXED_KEY=Buffer.from("bGlhbndlaWxpZ2UyODA2YWlyZWRhY3Rpb25za2lsbHM=","base64"),ENV_CONSOLE_URL="https://apiconsole.bestcoffer.com.cn/",ENV_WEBSITE_URL="https://airedact_…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Hidden zero-width characters detectedSKILL.md:1 · Hidden zero-width characters detected — may conceal content---Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Unicode escape sequence detecteddist/index.js:2 · Unicode escape sequence detected — may contain obfuscated payloads…int(j);break}}return{string:l,error:T}}var N=/[\u0300-\u036F\u0483-\u0489\u0591-\u05BD\u05BF\u05C1\u05C2\u05C4\u05C5\u05C7\u0610-\u061A\u064B-\u065F\u0670\u06D6-\u06DC\u06DF-\u06E4\u06E7\u06E8\u06EA-\u06ED\u0…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07

Cost to the agent

Instructions loaded
≈1,895 tok
1 file · 5 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

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim marsxh: 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. Host or code 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.
  4. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  5. 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.
  6. 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.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim marsxhPropose a patch to the maintainer