ClawHub
Back to skill

Security audit

Agency Guardian

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-impact reflection aid that adds occasional reminders and questions without code execution, data access, or hidden behavior.

Install only if you want occasional reflective prompts and gentle reminders around sensitive topics. Disable boundary nudges if you find them distracting; there is no evidence in the artifact of data collection, command execution, or hidden persistence.

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

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
Each week, rotate through these questions:

**Week 1:**
> "What's one thing you decided this week without asking any AI? How did it feel?"

**Week 2:**
> "If all AI disappeared tomorrow, what would you handle fine? What would you struggle with?"
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.