ClawHub
Back to skill

Security audit

council-of-wisdom-omni

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed markdown-only decision-support skill that routes through named analysis agents and asks before delegating to other workspace skills.

Install only if you want a skill that may structure answers through multiple advisory agents. Review any proposed delegation to other workspace skills before approving it, especially for sensitive or high-impact tasks.

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
94% confidence
Finding

This markdown file describes the skill's purpose in broad natural language ('How should this feel? Matches tone to user emotional state') but does not specify clear trigger phrases, scope limits, or negative examples. That ambiguity could cause unintended invocation from common conversational language about tone or feelings.

Content

No source excerpt is available for this finding.