ClawHub
Back to skill

Security audit

Feishu Rate Limit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Feishu/Lark API rate-limit guidance document, with no executable installer or hidden behavior, though its activation wording is somewhat broad.

Install this if you want Feishu/Lark API calls to use conservative pacing and retry guidance. Be aware it may slow Feishu-related workflows even when rate limits are not currently being hit, and review any local caching or .learnings error logs if your Feishu data is sensitive.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions are broad enough to activate on essentially any Feishu-related request, including generic mentions of 'Feishu API', 'Lark API', or 'rate limit', rather than only when a rate-limiting mitigation is actually needed. In an agent environment, this can cause the skill to inappropriately influence unrelated workflows, inject delays/retry logic where it is not applicable, and create unintended operational side effects such as slower execution or altered task behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.