ClawHub
Back to skill

Security audit

Decision Dynamo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local decision-matrix helper with no hidden persistence or network behavior; the main caveat is that its trigger phrases are fairly broad.

Before installing, be aware that the skill may activate for generic decision-help wording. It appears appropriate for local, structured comparisons, and users should review any JSON file they ask it to score because the script will read that specified file.

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 list includes broad, everyday phrases like "help me decide" and "which option is better," which can match many ordinary conversations and cause the skill to activate when the user did not explicitly want this tool. In this skill's context, the consequence is mainly unintended invocation and possible user confusion rather than direct security compromise, since the skill only performs a local decision-matrix workflow.

Static analysis

No suspicious patterns detected.