ClawHub
Back to skill

Security audit

Defense Rehearsal

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed academic defense rehearsal helper, but users should be mindful that its meeting-recording workflow can involve sensitive speech and transcript data.

Before installing, make sure you are comfortable sharing defense materials and Tencent Meeting recordings/transcripts with the relevant services, get consent from anyone participating in recorded mock defenses, and disable the local method-tag recording by saying '别记了' if you do not want usage tags retained.

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
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill promotes Tencent Meeting recording, transcript retrieval, and AI meeting minutes as core workflow features, but its high-level user-facing overview does not prominently disclose the privacy implications of capturing speech and processing meeting data. In an academic defense context, recordings may contain unpublished research, personal identifiers, or sensitive committee discussion, so insufficient up-front notice can lead to uninformed consent and inappropriate data exposure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file is natural-language documentation, and all user-facing content is presented only in Chinese. That can amount to a language/locale policy violation because the skill appears to force a specific language without user opt-in or a documented justification for limiting the skill to Chinese-language users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
61% confidence
Finding

The natural-language instructions and branding are primarily Chinese, with limited English supplementation, and do not state that users may choose their preferred language. This may conflict with an organizational language-choice policy if skills must not impose a locale without opt-in.

Content

No source excerpt is available for this finding.