ClawHub
Back to skill

Security audit

AI Automation Agency Blueprint

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only business playbook skill with disclosed agency-building advice and no executable behavior.

Before installing, treat it as business guidance rather than legal, financial, or security advice, and review any promoted external context packs or related skill installs separately before purchasing or installing them.

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

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README shows trigger-like commands such as "agency audit" and "agency model" in a Quick Start block, but it does not explain whether these are the only valid invocations, how matching works, or what should not trigger the skill. This ambiguity can cause unintended invocation behavior, especially since no negative examples or scope constraints are provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.