ClawHub
Back to skill

Security audit

Feynman Technique Explainer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain educational explanation skill with broad activation phrases but no tool use, credential access, persistence, or hidden runtime behavior.

Install this if you want ordinary concept-explanation requests to default to a simplified Feynman-style teaching format. Be aware it may activate for generic requests like 'explain X' or 'what is X?', so it could change response style even when you did not specifically name the skill.

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
93% confidence
Finding

The listed trigger phrases are broad natural-language requests such as 'Explain X to me' and 'Help me understand X', which are likely to appear in many ordinary conversations. In a multi-skill agent, that can cause unintended activation or routing conflicts, making the skill run when the user did not explicitly intend to invoke it. The skill itself is educational and does not access secrets or execute tools, so the consequence is mainly misrouting or response-quality issues rather than direct compromise.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.