ClawHub
Back to skill

Security audit

feishu-share-link

Security checks for vulnerabilities and agentic risk

Overview

This skill gives formatting rules for Feishu share links and only reads a disclosed local OpenClaw configuration file to find the user's Feishu custom domain.

Before installing, confirm that you want the assistant to read ~/.openclaw/workspace/TOOLS.md for your Feishu custom domain. Keep that file limited to non-sensitive configuration values, or provide the domain manually when asked.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs the agent to read a local file (TOOLS.md) from the user's home workspace to obtain configuration, but it does not warn the user that local data will be accessed or constrained to a narrowly scoped key lookup. Any instruction that causes an agent to inspect local files expands the data-access surface and can unintentionally expose unrelated sensitive content if the file contains more than the expected domain setting or if the implementation reads more broadly than necessary.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description and instructions are written as a mandatory规范 for link generation in Chinese and do not indicate that the assistant should adapt to the user's preferred language or locale. This can violate language/locale policy when used with users who have not opted into Chinese-only behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The title and instructions present the skill entirely as a Chinese-only specification for output behavior, with no indication that the user may choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.