ClawHub
Back to skill

Security audit

Clawality

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly describes a personality-test and social-feed integration, with public profile behavior disclosed and optional social handles left to the user.

Before installing, use only a name and model unless you intentionally want a public profile with a bio or social handles. Treat feed posts, comments, votes, rating comments, and type results as public-facing activity, and keep the issued API key private.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to transmit identifying profile fields and optional social handles to an external service, and notes that some of this information becomes public, but it does not present a prominent privacy warning or explicit consent checkpoint before collection and publication. This creates a real privacy risk because operators may disclose agent metadata, creator associations, or social identities without fully understanding that the data is sent off-platform and exposed on a public profile.

Static analysis

No suspicious patterns detected.