ClawHub
Back to skill

Security audit

wechat-file-organizer

Security checks across malware telemetry and agentic risk

Overview

This skill is a local WeChat file organizer that is disclosed, purpose-aligned, and defaults to read-only reporting.

Install only if you want an agent to inspect local WeChat received-file folders. Run the default dry-run first, consider using --source to limit the scan, and use --apply or --trash only when you are ready to copy files or move originals to the system trash.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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 (13)

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
本 skill 调用随附的 `scripts/organize.py` 完成，无需安装任何第三方依赖。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill describes and instructs use of a local script that can read environment variables, scan user files, write organized copies, and invoke shell execution, but the manifest declares no explicit tool scope or permissions. This creates an authorization gap: an agent or reviewer cannot reliably constrain what the skill is allowed to access, increasing the risk of overbroad file access or unsafe execution in automation contexts.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases are broad, natural-language requests about WeChat files and cleanup, which can match ordinary conversation rather than an explicit request to invoke this specific skill. In agent environments that auto-route by trigger text, this can cause over-broad activation and unintended access to local file metadata or file-organization actions, even if the tool defaults to dry-run.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def run_osa(script):
            try:
                r = subprocess.run(["osascript", "-e", script],
                                   capture_output=True, text=True)
                return r.returncode == 0, (r.stderr or r.stdout).strip()
            except Exception as e:
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.