ClawHub
Back to skill

Security audit

Feishu Book Match

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent book-matching purpose, but it can bulk-modify live Feishu Bitable records without requiring a preview or confirmation.

Install only if you are comfortable letting the agent update the target Feishu Bitable in bulk. Before running it, ask for a dry-run preview of affected records and proposed Amazon links, confirm the exact table and fields, and avoid unattended cron/background execution unless you have a rollback plan.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is broad enough to activate on loosely related requests such as general 'Amazon matching' or 'fill' tasks, which can cause the agent to run a workflow that reads and writes external Feishu records without sufficiently narrow user intent. In this skill, that broad activation is more dangerous because the workflow performs batch updates to a live Bitable and uses external search results to modify records.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to batch-update external Feishu records but does not require a user-facing warning or confirmation before modifying data. This is risky because an agent could silently overwrite many records, propagate incorrect Amazon matches, or make unauthorized changes to shared business data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.