ClawHub
Back to skill

Security audit

Feishu Readability

Security checks for vulnerabilities and agentic risk

Overview

This skill provides Feishu document formatting guidance and does not include hidden code, persistence, or unrelated access, though users should be aware it may steer document style choices.

Install this if you want agents to follow consistent Feishu document formatting and minimal-edit practices. For legal, compliance, multilingual, or externally governed documents, explicitly tell the agent to preserve the document's existing style guide instead of applying the localized formatting rules automatically.

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
89% confidence
Finding

The trigger conditions are broad enough to activate on common Feishu document editing requests, which can cause this skill to be loaded in many benign scenarios without explicit user intent. Because the skill then imposes prescriptive editing behavior and modification rules, it can steer agent behavior beyond the user’s requested scope and increase the chance of unnecessary or policy-altering document changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill mandates localized Chinese formatting conventions, such as colon placement and punctuation removal, without requiring user opt-in or checking the document’s language/style guide. This can silently alter meaning, house style, or compliance-sensitive wording in documents that are multilingual, externally facing, or governed by a different editorial standard.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.