ClawHub
Back to skill

Security audit

IDA: Instructional Design Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain instructional-design helper that produces learning strategy blueprints and does not request privileged system access.

Installers should still review any client or SME documents before sharing them with the agent, because the skill is designed to process potentially sensitive business and training context. The optional agent execution manifest should be requested only when planning downstream automation, but the artifact keeps it structural and calls for human approval points.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 340)May include surrounding context.

md
- Human Review Checklist
- Optional sections (if explicitly requested)

Do not continue generating beyond scope.

Static analysis

No suspicious patterns detected.