ClawHub
Back to skill

Security audit

Context Budget Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only guidance skill for reducing AI context costs, with no hidden code or unrelated data handling found.

Install only if you want advice on reducing AI context and token costs. Before following its recommendations, review any proposed deletions, archives, memory summaries, system-prompt edits, skill-loading changes, or AGENTS.md model-routing changes so important context is not lost or made harder to access.

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
92% confidence
Finding
The example trigger 'Use the [skill-name] skill' is a generic natural-language pattern that could overlap with ordinary user requests, and the document does not define exclusion conditions or a narrow activation context. Because this markdown file describes lazy-loading behavior, the lack of specificity may cause unintended skill invocation.

Static analysis

No suspicious patterns detected.