ClawHub
Back to skill

Security audit

Project

Security checks for vulnerabilities and agentic risk

Overview

This is a project-management memory skill with no executable code, and its sensitive behaviors are disclosed and aligned with its stated purpose.

Install only if you are comfortable letting the agent remember project details such as clients, budgets, timelines, blockers, and team performance. Use explicit wording for updates and review status reports or escalations before sending them outside the 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
91% confidence
Finding
The skill describes broad conversational behaviors like updating trackers when users 'mention in a chat' that work is done or someone is blocked, without defining explicit trigger boundaries or confirmation requirements. In a chat environment, this can cause unintended activation from incidental conversation, quoted text, hypotheticals, or third-party content, leading to unauthorized state changes, inaccurate project records, or accidental disclosure/escalation actions.

Static analysis

No suspicious patterns detected.