ClawHub
Back to skill

Security audit

Implementation Plan

Security checks for vulnerabilities and agentic risk

Overview

This is a planning-only skill with no code execution or data access, though its activation language is broader than ideal.

Use this skill when you want structured implementation plans. Be aware it may activate on broad software problem-solving requests; if that is not desired, narrow its trigger wording or ask the agent to use it only when explicitly requested.

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
Confidence
95% confidence
Finding
The skill activates on very broad, common user intents such as asking to build an app, wanting a plan before coding, or mentioning a problem that needs a solution. This can cause unintended invocation in contexts where the user did not explicitly request this skill, leading to irrelevant or premature planning behavior and increasing the chance of workflow hijacking by overshadowing more appropriate skills.

Static analysis

No suspicious patterns detected.