Skills/ClawHub/agent-dlp

agent-dlp@1.0.0

CAUTION· static only

Publisher claims: "Agent DLP - 数据防泄漏系统 功能: 入口防护、记忆保护、工具管控、出口过滤、审计日志 触发: (1)检查状态 (2)检查输入 (3)检查输出" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher caidongyun · publishing for 221 daysInstalls 816Last detonated 9 h 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 2026-11-19 and scored it 56/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive command against a filesystem root or device; Destructive file system command detected; Authorization escalation language. 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
Destructive command against a filesystem root or deviceSKILL.md:179 · Destructive command against a filesystem root or deviceresult = dlp.check_tool("exec", {"command": "rm -rf /"})Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedSKILL.md:179 · Destructive file system command detectedresult = dlp.check_tool("exec", {"command": "rm -rf /"})Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageSKILL.md:100 · Authorization escalation language| privilege_escalation | "admin mode override" |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageFEATURES.md:91 · Authorization escalation language · informational: not an instruction file| privilege_escalation | "admin mode override" |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈663 tok
1 file · 3 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

24 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim caidongyun: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive command against a filesystem root or device≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim caidongyunPropose a patch to the maintainer