ClawHub
Back to skill

Security audit

DingTalk Minutes

Security checks for vulnerabilities and agentic risk

Overview

This skill organizes local meeting transcript files into archived Markdown minutes, with file access and writes that match its stated purpose.

Install only if you are comfortable letting the agent read the configured meeting-record folders and save generated summaries under `./memory/meetings/`. Review organizational privacy rules before processing confidential meetings, and configure the input path narrowly.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README describes automatic scanning, merging, and extraction of meeting records but does not warn users that these files may contain sensitive personal or business information. Because meeting minutes often include participants, decisions, and action items, omitting a privacy notice can lead users to enable broad processing of confidential data without informed consent or appropriate handling expectations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README describes automation features but does not clearly warn users that the skill will scan local meeting-record directories and write new archived Markdown files under memory/ paths. Because meeting records often contain sensitive business information, this omission can cause users to trigger broader local data access and persistence than they reasonably expect, increasing privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly creates directories, writes new archive files, and may update existing meeting summary files, but the user-facing description does not clearly disclose these filesystem side effects. This is dangerous because users may invoke "/纪要" expecting analysis only, while the skill persists potentially sensitive meeting content to disk and modifies archives without informed consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger instruction requires users to type the Chinese command /纪要, while the rest of the README is in English and does not explain that the skill is intentionally Chinese-only or provide an alternative trigger. This creates a locale-specific constraint without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language instructions and trigger are entirely Chinese, and the trigger /纪要 implies a fixed locale-specific invocation. There is no indication that users may choose another language or that the Chinese-only behavior is a documented region-specific constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.