ClawHub
Back to skill

Security audit

Agent Governance Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only governance template skill with broad but purpose-aligned triggers and no tool, persistence, or credential behavior.

Use this skill as a governance and report-drafting aid, not as a live compliance scanner or legal opinion. Verify current regulatory statements with official sources and internal counsel before using outputs for formal decisions or external filings.

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
92% confidence
Finding

The trigger list contains several broad, generic phrases such as "agent governance," "enterprise AI compliance," and "AI risk report" that can match ordinary user requests without sufficient scoping. This can cause the skill to activate outside its intended context, leading to overbroad governance/compliance guidance being injected into unrelated workflows and increasing prompt-surface exposure to any unsafe instructions embedded in the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.