ClawHub
Back to skill

Security audit

Shadows Project Architect

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only project-planning skill with no bundled code, commands, network behavior, or persistence, though its trigger wording is somewhat broad.

Install this if you want Codex to use a structured planning format for new projects or major features. Be aware it may activate on broad planning words, so decline or redirect it when you only want a quick answer or small implementation change.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad, common phrases such as "plan this," "architect," and "design the system," which can match normal conversational requests outside the intended scope. This can cause unintended invocation of the skill, leading the agent to switch into a structured planning workflow when the user wanted a simpler or different action, increasing the chance of workflow hijacking or unnecessary data collection through follow-up questions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.