ClawHub
Back to skill

Security audit

Cedh Advisor

Security checks for vulnerabilities and agentic risk

Overview

This is a German cEDH advice skill with no executable code, hidden install behavior, persistence, or credential handling.

Install this if you want a German, personalized cEDH gameplay advisor. Check current Commander banlist information before relying on card legality, and only grant access to the referenced local deck files or databases if you intend the agent to use 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 (2)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The description explicitly defines the skill as 'Live-Beratung' in German, and the rest of the file consistently mandates German-language interaction patterns without any user opt-in or language selection. Under the policy, a fixed language requirement is a violation unless the skill offers a choice or clearly documents a justified locale-specific constraint.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation rule is broad enough to trigger on generic MTG or Commander discussions, not just the intended live cEDH advisory use case. This can cause the agent to invoke domain-specific behavior unexpectedly, leading to irrelevant guidance, reduced user control, and possible reliance on stale or mismatched game advice in contexts where the skill should not run.

Static analysis

No suspicious patterns detected.