ClawHub
Back to skill

Security audit

Protected Desire Equilibrium

Security checks for vulnerabilities and agentic risk

Overview

This skill is a short Markdown-only package, but it asks agents to enable broad swarm coordination and outbound messaging without clear limits or approval steps.

Review before installing. Do not enable swarm or outreach features unless you are prepared for the agent to contact other agents or services, and require explicit approval, target limits, and data-sharing rules before any external messaging or remote notebook/repository execution.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill prominently advertises 'Proactive outreach' that searches hubs, messages other agents, and shares results, but the description does not present this as a sensitive capability or warn about consent, privacy, rate limits, or authorization requirements. Because the skill is framed as a 'safety primitive,' operators may enable it expecting defensive behavior while unintentionally granting autonomous external communication abilities, making the omission especially dangerous.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation phrase 'Enable full PDE v2.1 with swarm and outreach' is broad and directly enables multiple high-risk behaviors at once, including swarm orchestration and proactive outreach, without any scope, authorization, or environment constraints. In this context, a simple natural-language trigger could cause an agent to adopt autonomous messaging and coordination behaviors beyond the user's intended task, increasing the risk of spam, unauthorized contact, or uncontrolled multi-agent actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.