Back to skill

Security audit

meeting-notes

Security checks for vulnerabilities and agentic risk

Overview

This is a simple meeting-notes formatting skill with no code, hidden system access, or persistence.

This skill is appropriate for organizing meeting notes. Users should still avoid pasting sensitive transcripts unless they are comfortable sharing that content with their agent environment, and they may want clearer trigger wording if they often ask for non-meeting summaries.

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)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description lists triggers such as "帮我总结这次会议" and "meeting summary," which can overlap with ordinary summarization requests rather than clearly signaling this specific skill. The file also does not provide exclusion conditions or negative examples to clarify when general summarization tasks should not invoke the meeting-notes skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
62% confidence
Finding

The file presents the skill primarily in Chinese while also prescribing specific English trigger phrases, but it does not explicitly state that users may choose their preferred language or locale. If organizational policy requires avoiding implicit language assumptions, this could be interpreted as forcing a language pattern without opt-in.

Content

No source excerpt is available for this finding.