ClawHub
Back to skill

Security audit

Aunkar Social Draft

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple social-media drafting helper with a slightly broad trigger, but it does not request account access, run code, persist data, or post anything automatically.

Use this skill when you specifically want Twitter/X and LinkedIn draft copy. Because its trigger includes the generic phrase 'draft a post,' users may need to clarify when they want a non-social-media post, but there is no artifact evidence of automatic posting, credential use, file access, or hidden execution.

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
Confidence
95% confidence
Finding
The trigger condition is broad enough to activate on common, ambiguous requests such as 'draft a post' or 'write social content,' which can cause the wrong skill to run when a user only wants generic writing help. In an agent setting, over-broad routing can bypass more appropriate skills or constraints and lead to unintended handling of user data or outputs.

Static analysis

No suspicious patterns detected.