ClawHub
Back to skill

Security audit

会议周报/复盘自动生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly focuses on turning meeting notes or Tencent Meeting data into reports, with no hidden exfiltration or destructive behavior found.

Install only if you are comfortable letting the agent summarize meeting notes or Tencent Meeting records. For sensitive teams, specify the exact date range, meetings, or local notes directory, and review generated reports before allowing any backfill, sharing, or push to participants.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill instructs the agent to read local materials and write output files, but no explicit permissions are declared. This creates a capability/authorization mismatch: the runtime or reviewer cannot clearly constrain or audit file access scope, increasing the chance of overbroad reads of local notes or writes to unintended paths.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The README advertises broad natural-language triggers such as '生成本周周报' and '会议复盘' without defining clear scope, boundaries, or confirmation requirements. In an agent environment, overly permissive activation can cause the skill to run on loosely related requests, leading to unintended aggregation of meeting transcripts or summaries and possible exposure of sensitive cross-meeting information.

Vague Triggers

Medium
Confidence
79% confidence
Finding
The trigger phrases are broad and cover common summarization/reporting requests without clear exclusion conditions. That can cause unintended activation in contexts where the user did not intend meeting-data aggregation, potentially leading to unnecessary access to local notes or connected meeting records and accidental exposure of sensitive business information.

Static analysis

No suspicious patterns detected.