ClawHub
Back to skill

Security audit

distill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow for turning session lessons into user-controlled persistent notes, rules, skills, or decision records.

Install this only if you want an explicit end-of-session workflow that may update persistent agent knowledge. Before accepting its output, review the allocation table and confirm any global rules or memories are truly meant to affect future sessions.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md
> **Fill in paths and naming conventions for your own project and IDE.** This document uses placeholder notation and is not tied to any specific toolchain.
>
> **Prerequisite**: your agent already has (or you want to build) all four of these — persistent rules, persistent memory, skills, and decision records. If all you have is a single markdown notebook, this layering is over-engineering — just write it down.

## 1. Scan the session for distillable signals