ClawHub
Back to skill

Security audit

AANA Publication Check Skill

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill provides a public-publication review checklist and does not install, execute, persist, or transmit anything on its own.

Installers should expect the skill to add a conservative review step before public or external content is published. If using an optional AANA checker, configure only trusted host tools or connectors and send redacted summaries rather than raw private material.

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 instruction to use this skill whenever an agent may "publish, update, send, post, release, or prepare public-facing content" spans a very wide range of routine activities and does not define boundaries or negative examples. This ambiguity could cause the skill to be invoked for ordinary drafting or communication tasks that are not truly publication-sensitive.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.