Back to skill

Security audit

微信文件自动归类

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because the scanner reports a risk of irreversible file deletion and could not fully inspect part of its organizer script.

Consider not installing until the organizer’s cleanup behavior has been reviewed and the script’s incomplete analysis has been resolved. The main reported concern is possible permanent deletion of source files; the scan does not establish malicious intent.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (15)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
本 skill 调用随附的 `scripts/organize.py` 完成,无需安装任何第三方依赖。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

md
脚本位置:`scripts/organize.py`(本 skill 目录内)。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
python scripts/organize.py

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

md
python scripts/organize.py --apply --scheme type-month

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
python scripts/organize.py --apply --dedupe

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
python scripts/organize.py --apply --trash

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

md
python scripts/organize.py --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md
python scripts/organize.py --source "/path/to/xwechat_files" --apply

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
python scripts/organize.py --lang en # English

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

md
WFO_LANG=en python scripts/organize.py # 或用环境变量

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 121)May include surrounding context.

md
| 能力 | 无头脚本 `organize.py` | GUI 应用 `main.py` |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.

md
若 `scripts/organize.py` 丢失,本 SKILL.md 已完整描述接口与参数;最稳妥的方式是从

Windows cleanup can permanently delete source files despite the manifest's guarantee that this never happens.

High
Category
Excessive Agency
Confidence
97% confidence
Finding

FOF_ALLOWUNDO requests recoverable deletion but does not guarantee it: SHFileOperationW can permanently delete files where recycling is unavailable, such as some network locations. Combined with suppressed confirmation and error UI, this violates the advertised recoverable-only cleanup contract; a successful copy reduces immediate data-loss risk but does not preserve the promised recovery of source files.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/organize.py (reported line 459)May include surrounding context.

python
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: