ClawHub
Back to skill

Security audit

MECE (Mutually Exclusive, Collectively Exhaustive)

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a structured thinking method without requesting sensitive access or authorizing consequential actions.

Use this as a thinking aid and independently verify important conclusions. If recording failure examples in the skill, avoid including confidential details.

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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 107)May include surrounding context.

md
- "These are MECE" stated without overlap and gap tests
- An "Other" category capturing > 30% of the whole
- Categories that share obvious cases (e.g., "Big customers" and "Important customers")
- The decomposition was inherited / copied without checking
- The branches don't sum to the original whole
- Only one decomposition dimension was considered
- The decomposition goes 5+ levels deep without action at the leaves

Static analysis

No suspicious patterns detected.