ClawHub
Back to skill

Security audit

logic

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed reasoning aid with limited local persistence and no evidence of hidden execution, credential access, network use, or destructive behavior.

Install this if you want the agent to use a persistent reasoning framework across sessions. Be aware it may create and maintain files under ~/logic/ and may shape a wide range of strategic, diagnostic, and decision-making answers, so review that directory if you do not want long-lived reasoning notes.

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
93% confidence
Finding
The 'When to Use' section lists general conditions like ambiguous requests, tradeoffs, diagnosis, or meaningful-cost answers, which apply to a very large share of ordinary conversations. It does not provide exclusion conditions or negative examples, so the activation scope is not clearly bounded.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs initialization under `~/logic/` and describes persistent files in the user's home directory without requiring explicit user consent or warning about local writes. In an agentic environment, this can lead to unauthorized persistence, unexpected disk modifications, and storage of potentially sensitive reasoning artifacts across sessions.

Static analysis

No suspicious patterns detected.