ClawHub
Back to skill

Security audit

飞书知识库查询

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Feishu knowledge-base lookup helper with no bundled code, installation behavior, persistence, or hidden privileged actions.

Install this if you want the agent to consult the named Feishu openclaw knowledge base during relevant tasks. Review the knowledge-base permissions and contents, because fetched documents may influence the agent's work; narrow trigger wording would reduce accidental lookups.

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
  • 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

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger examples are broad natural-language phrases such as '参考之前' and '确认一下之前的操作', which can appear in many ordinary conversations and may invoke the skill outside the author's intended scope. In a knowledge-query skill, over-triggering can cause unnecessary retrieval of internal documentation, unintended context injection into downstream actions, and possible exposure of sensitive operational information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill metadata and instructions are entirely written as Chinese-only user-facing guidance, with no indication that language selection is optional or limited for a documented region-specific reason. Under the policy, a fixed language or locale should either be user-selectable or explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.