ClawHub
Back to skill

Security audit

mise

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a disclosed design-and-approval workflow, with no evidence of hidden or harmful behavior.

Expect approval steps even for small changes, repository inspection, and a specification committed under docs/specs. The referenced pressure-test and recipe skills are separate dependencies whose contents were not included in this package.

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)

The activation condition covers any creative or build work, without clear exclusions.

Medium
Category
Trigger Abuse
Confidence
88% confidence
Finding

The description activates the skill before "any creative or build work," and the instructions extend the mandatory design process to "every task," including small changes. This broad scope can invoke a full design-and-approval workflow for routine edits or creative requests that do not need engineering design.

Content

No source excerpt is available for this finding.