ClawHub
Back to skill

Security audit

CCPA Compliance

Security checks across malware telemetry and agentic risk

Overview

This is a local CCPA/CPRA compliance helper whose file access and report writing are disclosed and aligned with its purpose, with some documentation and dependency hygiene issues to consider.

Review this as a local compliance aid, not legal advice. Before installing dependencies, consider pinning or auditing pandas and jinja2, and be careful with any --output path because reports are written wherever you direct them. The skill appears local-only, but some docs reference missing or outdated scripts and versions, so verify the commands you plan to use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill advertises and instructs use of local Python scripts that can read files, write reports, and invoke shell commands, yet it declares no permissions. This creates a capability/permission mismatch that can mislead users or enforcement systems about what the skill can actually do, reducing transparency and increasing the chance of unintended file access or command execution.

Vague Triggers

Medium
Confidence
77% confidence
Finding
The trigger keywords include broad terms such as privacy, data protection, consumer rights, and California privacy, which can match many unrelated conversations. Over-broad activation can cause the skill to engage in contexts where it is not appropriate, increasing the risk of accidental access to sensitive compliance discussions or files and creating prompt-scope confusion.

Unpinned Dependencies

Low
Category
Supply Chain
Content
# Ccpa-compliance Skill - 纯本地合规检查工具
# 所有依赖版本锁定以确保运行稳定

pandas>=2.0.0
jinja2>=3.1.6
Confidence
92% confidence
Finding
Using a lower-bound-only dependency specifier for pandas allows future unreviewed versions to be installed, which can introduce breaking changes or newly disclosed supply-chain vulnerabilities. In a compliance tool, report generation and data processing may handle sensitive business or consumer information, so dependency drift increases operational and security risk even though the tool claims local-only execution.

Unpinned Dependencies

Low
Category
Supply Chain
Content
# 所有依赖版本锁定以确保运行稳定

pandas>=2.0.0
jinja2>=3.1.6
Confidence
93% confidence
Finding
Using jinja2>=3.1.6 permits automatic installation of any newer release, including versions not yet vetted by the skill author. Because Jinja2 is often used for templated report generation, dependency drift could expose the tool to template-related security regressions or other supply-chain issues if a compromised or vulnerable release is pulled in.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.