ClawHub
Back to skill

Security audit

PC 200

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow ClawHub file-count publishing probe made of tiny synthetic files, with no hidden code or persistence found.

Install only if you intend to run a ClawHub publishing limit probe. Use synthetic, non-sensitive test files and expect possible publish failures or rate-limit effects while testing the threshold.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly describes publishing an exact number of files to an external service in order to probe a platform limit, but it does not warn the user that it will transmit files off-system as part of that test. This creates a transparency and consent problem and could lead users to unknowingly send data externally or trigger rate-limit / abuse controls while diagnosing a 413 threshold.

Content

No source excerpt is available for this finding.