Back to skill

Security audit

腾讯会议录制纪要&待办

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Tencent Meeting recording workflow that handles sensitive meeting content but includes clear user-control and privacy guardrails.

Install only if you intend to let the agent work with Tencent Meeting recordings and transcripts available through your tmeet login. Be careful with playback/download links because they may contain temporary credentials, and review permission-apply confirmations before approving any real access request.

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
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is written entirely in Chinese and specifies user-facing output structure in Chinese, but it does not state that language choice is optional or user-selected. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is clearly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The default activation prompt is very broad and encourages the agent to invoke a powerful recording/transcript workflow whenever a user mentions related topics, without requiring explicit confirmation, scope limits, or authorization checks. In a skill that can access meeting recordings, summaries, transcripts, and access-request handling, overly permissive triggering increases the chance of unintended data retrieval or disclosure from sensitive corporate meetings.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.