ClawHub
Back to skill

Security audit

kleos

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Kleos connector for creating, scheduling, and measuring TikTok and Instagram posts, with sensitive social-account actions described and generally gated by user login or confirmation.

Install only if you intend to let Kleos manage real social-media production. During OAuth or API-key setup, grant only the scopes you need, review the selected organization and project, and require explicit confirmation before posts are scheduled, published, deleted, or team/account settings are changed.

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 skill declares many broad trigger phrases such as 'schedule posts on TikTok/Instagram', 'connect my TikTok', and generic social-media planning requests, which can cause the skill to activate in response to common user prompts that are not clearly intended to invoke this specific external integration. Because this skill has access to high-impact actions through MCP, including account connection, publishing, and team-related operations, overbroad invocation increases the risk of accidental tool use and unintended actions on real social accounts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.