ClawHub
Back to skill

Security audit

Feynman Cognition — Cognitive Atom Deconstruction Framework

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain educational explanation framework with no code execution, data access, persistence, or hidden installation behavior.

Install this if you want detailed, structured explanations of concepts. Be aware it may activate on fairly general requests for clarity and produce a longer five-part answer than you intended.

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
96% confidence
Finding

The activation criteria use broad, common phrases such as 'make this clear,' 'help me break this down,' and 'explain from a different angle,' which can match many ordinary user requests. This can cause unintended skill invocation, overriding more appropriate routing and making the assistant follow a rigid multi-step framework when the user did not ask for it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.