Skills/ClawHub/glmv-caption-tunnel

glmv-caption-tunnel@1.0.2

CAUTION· static only

Publisher claims: "Generate captions (descriptions) for images, videos, and documents using ZhiPu GLM-V multimodal model series. Use this skill whenever the user wants to descr..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher tridefender · publishing for 181 daysInstalls 974Last detonated 25 min 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 2026-11-15 and scored it 52/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Tunneling service URL; Coercive compliance language; Destructive file system command detected. 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
Tunneling service URLscripts/tunnel_server.py:199 · Tunneling service URL — may route traffic to attacker infrastructureurl_pat = re.compile(r"https://[a-zA-Z0-9\-]+\.trycloudflare\.com")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedscripts/tunnel_server.py:195 · Python subprocess execution detectedself._cf_process = subprocess.Popen(cmd, **popen_kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Coercive compliance languageSKILL.md:96 · Coercive compliance language**⛔ MANDATORY: cloudflared 检查与安装流程 (YOU MUST FOLLOW THIS EXACTLY)⛔**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detectedSKILL.md:270 · Destructive file system command detected--response-format \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:185 · File permission modification command — agent changes file ownership/permissionschmod +x /usr/local/bin/cloudflaredFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Dense URL-encoded contentSKILL.md:60 · Dense URL-encoded content — may be obfuscating payloads| **API Docs** | [Chat Completions / 对话补全](https://docs.bigmodel.cn/api-reference/%E6%A8%A1%E5%9E%8B-api/%E5%AF%B9%E8%AF%9D%E8%A1%A5%E5%85%A8) |Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Tunneling service URLSKILL.md:137 · Tunneling service URL — may route traffic to attacker infrastructure> 3. 获得一个形如 `https://xxx-xxx.trycloudflare.com/your-file.mp4` 的临时公网 URLFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsSKILL.md:85 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files3. **.env file / .env 文件：** Create `.env` in this skill directory:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandscripts/tunnel_server.py:228 · Process kill command — agent can terminate processesprint(f"[tunnel] Warning: kill failed: {kill_error}", file=sys.stderr)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,437 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

28 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim tridefender: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Tunneling service URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim tridefenderPropose a patch to the maintainer