ClawHub
Back to skill

Security audit

Virtual Board of Advisors

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill provides disclosed business advisory templates and references, with no evidence of hidden access, execution, persistence, or data exfiltration.

Before installing, be aware that asking for a report or deep dive may generate a large response and use more tokens. The skill asks for business context and includes fitness/nutrition and AI strategy material, so treat outputs as strategic guidance rather than licensed medical, legal, or professional advice.

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
88% confidence
Finding

The deep-report trigger is defined by broad natural-language terms like "report," "deep dive," or "full analysis," which can be invoked unintentionally during ordinary conversation. This can cause the skill to load additional reference material and generate very large outputs without clear user confirmation, increasing token consumption, latency, and the chance of context-window crowding or accidental instruction interactions from loaded files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.