Security audit

GDPR Compliance

Security checks across malware telemetry and agentic risk

Overview

This skill is a local GDPR report and template helper, with some documentation and dependency hygiene issues but no evidence of hidden data access, network transfer, or destructive behavior.

Before installing, understand that this is not legal advice and that generated reports may contain business or privacy-sensitive information. Run it in a working directory where local report files are acceptable, avoid overwriting important files with --output paths, and consider pinning dependency versions if you need reproducible installs.

SkillSpector

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 78% confidence
Finding: The skill declares no permissions while its documented behavior includes writing reports to user-specified files. This creates a transparency and least-privilege issue: users and any permission-gating system may underestimate what the skill can do, increasing the chance of unauthorized or unsafe file writes.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 83% confidence
Finding: The skill description understates and inconsistently describes actual capabilities, including template generation, validation utilities, and report-formatting behaviors beyond the main checker flow. Description-behavior mismatches are dangerous because they erode user trust and can conceal risky functionality or cause users to invoke the skill under false assumptions about what it will generate or write.

Vague Triggers

Medium

Confidence: 74% confidence
Finding: The trigger keywords are broad and overlap with ordinary privacy or compliance discussions, which can cause the skill to activate in contexts where the user did not intend to run it. Unintended activation is risky because the skill can generate files and guide compliance actions based on partial or irrelevant context, increasing confusion and accidental data exposure in reports.

Vague Triggers

Medium

Confidence: 76% confidence
Finding: The secondary trigger list is expansive and ambiguous, further increasing the chance of accidental invocation during general legal, privacy, or training conversations. In a compliance skill that can produce reports and templates, unintended activation may lead to misleading outputs, unnecessary file writes, or users relying on outputs outside the intended jurisdiction or use case.

Unpinned Dependencies

Low

Category: Supply Chain
Content: # Gdpr-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: 93% confidence
Finding: The dependency is not fully pinned, so installations may resolve to different pandas versions over time, including future releases with breaking changes or newly introduced malicious/compromised transitive content. In a security-sensitive compliance tool, this weakens supply-chain integrity and reproducibility even if the tool claims to run locally and without network access at runtime.

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: 95% confidence
Finding: Using jinja2>=3.1.6 permits any later version, which creates supply-chain risk because future versions may introduce vulnerabilities, behavioral changes, or compatibility issues that alter tool output. Since Jinja2 is often involved in report generation and templating, uncontrolled upgrades can affect both security posture and output trustworthiness.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.