ClawHub
Back to skill

Security audit

Blocker Minimum Input

Security checks for vulnerabilities and agentic risk

Overview

This skill only teaches the agent how to report blockers clearly and does not add hidden access, persistence, code execution, or data handling.

Installing this skill should be low risk. Expect it to make the agent more structured when blocked; review blocker reports for redacted secrets and avoid pasting real tokens or sensitive paths back into chat.

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 trigger section says to use the skill when 'User input required to proceed' and 'Permission/auth issues detected,' which are broad situations that can occur across many unrelated tasks. Without tighter scope or exclusion conditions, this could cause the skill to activate in routine conversations or generic troubleshooting contexts.

Static analysis

No suspicious patterns detected.