ClawHub
Back to skill

Security audit

Lofy Projects

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward project-management skill that stores project notes in a local JSON file, with some caution needed around automatic record updates.

Install only if you want the assistant to maintain a local project record. Review or back up data/projects.json periodically, and ask the assistant to show proposed changes before saving if you do not want casual project comments recorded automatically.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description is broad enough to match many ordinary productivity conversations, which can cause the skill to activate outside the user's intended context. Over-broad activation increases the chance the agent will read or act on persistent project data during unrelated chats, creating privacy and integrity risks through unnecessary invocation.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The instruction to update persistent JSON after any project conversation creates hidden state changes without explicit user awareness or consent. In practice, casual remarks could be converted into durable records, causing inaccurate project data, privacy issues, and unintended automation based on misunderstood conversation content.

Static analysis

No suspicious patterns detected.