ClawHub
Back to skill

Security audit

vow-enforcement

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill gives guidance for classifying and enforcing project rules, with no hidden code, persistence, or automatic privileged actions.

Install this if you want an agent to reason about when project rules should be soft guidance, hooks, or validator checks. Be aware that its broad trigger words may bring it into general compliance or governance conversations, so review whether that activation behavior fits your workflow.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad, common terms like "hooks," "compliance," "governance," and "enforcement," which can cause the skill to activate in many unrelated contexts. Because this skill is about imposing constraints and routing decisions through enforcement layers, accidental activation could steer an agent toward unnecessary blocking behavior or governance logic where it was not intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.