ClawHub
Back to skill

Security audit

Cross Domain Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a research-framing skill with broad speculative analysis prompts, but it does not include executable code, credential access, network calls, installation hooks, or hidden behavior.

Install only if you want a speculative research aid. Do not treat its correlations as verified investment, cybersecurity, patent, or business advice without independent evidence and human review, especially because the referenced implementation file is absent.

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)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description is broad enough to match many generic research, analysis, threat-intelligence, and investment-related tasks, which can cause the agent to invoke this skill outside a narrowly intended scope. Overbroad activation increases the chance of unintended delegation, making it easier for the skill to influence decisions or outputs in unrelated contexts.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The 'When to Use' section gives expansive activation cues such as investment signals, threat cross-referencing, and patent mining without boundaries, approval requirements, or disallowed scenarios. In an agentic system, ambiguous triggers can cause opportunistic invocation on sensitive tasks, including high-stakes analysis where speculative cross-domain correlations may mislead operators or bypass safer specialized tools.

Static analysis

No suspicious patterns detected.