ClawHub
Back to skill

Security audit

compliance-auditor

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only compliance checklist skill that is broad in scope but does not install code, run commands, persist, or access data by itself.

Install only if you want checklist-style compliance audit support. Have qualified legal, privacy, or security professionals review conclusions before relying on them for regulatory decisions, breach notification, certification, or production security design.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises very broad activation triggers such as 'regulatory expertise' and 'data processing' without clear boundaries for when it should or should not engage. In agent routing systems, this can cause the skill to be invoked for generic legal, security, privacy, or governance requests outside its intended scope, increasing the chance of overreach, misrouting, or unsafe authoritative guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The usage examples and best-practices section show many ways to invoke the skill but do not define exclusion criteria or refusal boundaries. That makes the skill more likely to handle ambiguous requests, including ones that should be routed to legal counsel, privacy counsel, or security engineering, which can lead to inaccurate compliance conclusions presented with undue authority.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.