ClawHub
Back to skill

Security audit

Context Slimmer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused context-file auditing helper with read-only measurement tooling, but users should review any proposed edits to sensitive agent instruction or memory files.

Install only if you want help auditing always-loaded context files. Treat its recommendations as proposals: review changes to AGENTS.md, MEMORY.md, USER.md, SOUL.md, HEARTBEAT.md, TOOLS.md, or IDENTITY.md before applying them, because those files may affect future agent behavior.

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
Confidence
93% confidence
Finding
The trigger description is broad enough that the skill may activate for generic requests like reducing tokens, optimizing context, or slimming workspace files, even when the user did not specifically intend to modify always-loaded context files. That can cause unnecessary inspection or modification of high-sensitivity instruction files such as AGENTS.md, MEMORY.md, or IDENTITY.md, increasing the chance of accidental policy loss or context corruption.

Static analysis

No suspicious patterns detected.