Back to skill

Security audit

Meeting Copilot

Security checks for vulnerabilities and agentic risk

Overview

This skill locally formats user-provided meeting information into Chinese meeting briefs, minutes, and follow-up drafts without network access, persistence, or automatic sending.

Install this if you want a Chinese-language meeting operations helper that produces drafts only. Review outputs before using them for business decisions or sending them, since the skill does not verify facts and relies entirely on the meeting details you provide.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file includes natural-language descriptions and generated output templates that are primarily Chinese, and the interface/error messages later in the file also assume Chinese output. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation unless the constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language description is written as a Chinese-first skill description and presents the skill behavior without any indication that users may choose another language or locale. Under the policy, language or locale constraints should be optional or explicitly justified; this file does neither.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description and heading present the skill in Chinese while embedding English terms such as 'Copilot', 'boss mode', and 'executor mode', and the rest of the file continues this mixed-language pattern. Because the skill does not explicitly offer users a language/locale option or justify this as a region-specific skill, it may violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code file contains natural-language strings such as the module docstring and test runner messages in Chinese, which effectively imposes a specific language on users or maintainers interacting with the skill. The policy allows locale constraints only when justified or when users are given a choice, neither of which is indicated here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.