ClawHub
Back to skill

Security audit

disclosure-page-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple disclosure-page writing guide with no executable code, persistence, network access, or credential handling.

Review that this skill is intended for affiliate, sponsorship, FTC, and paid-partnership disclosures; for unrelated legal, privacy, financial, or security disclosure work, use a more specific skill or ask the agent to avoid this one.

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 text is broad enough to activate on generic uses of the word 'disclosure,' which can cause the wrong skill to run for unrelated legal, privacy, financial, or security disclosures. In an agent system, this misrouting can produce irrelevant or incomplete compliance guidance, increasing the chance of user confusion or omission of more appropriate safeguards from other skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.