ClawHub
Back to skill

Security audit

Circle of Competence

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed decision-coaching framework and I found no hidden execution, persistence, or data-access behavior.

This appears safe to install as a reasoning aid. It may steer an agent to slow down, defer, or size down consequential decisions outside the user's expertise, so users should treat it as coaching rather than authoritative investment, hiring, legal, or business advice.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

md
*→ 2026 lens: [Funding and Building AI Outside Your Circle (2024–2026)](examples/ai-hype-outside-the-circle-2024-2026.md)*

Static analysis

No suspicious patterns detected.