ClawHub
Back to skill

Security audit

ELI5

Security checks for vulnerabilities and agentic risk

Overview

This is a simple explanation-formatting skill with optional web fetching, and its behavior is disclosed and proportionate.

Installers should understand that the skill is mainly prompt instructions. Use fetch only for topics you are comfortable sending to web search, and set ELI5_DEFAULT_LANG or /eli5 lang if English is not the desired default.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README promotes automatic web fetching and per-query --fetch without clearly warning that user prompts or concepts may be transmitted to external services. This creates a real privacy and data-handling risk, especially if users enter sensitive topics assuming the skill is purely local or self-contained.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README states a language priority ending in 'fallback English', which imposes a specific language when neither environment nor command selection is set. This is a locale/language policy concern because the skill defaults to a language without explicit user opt-in at that point.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.