ClawHub
Back to skill

Security audit

codebase-explainer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed codebase-onboarding helper that reads repository structure and writes an ONBOARDING.md file, with no evidence of hidden execution, exfiltration, or persistence beyond that document.

Install this if you want an agent to produce a durable onboarding document for a repository. Be aware that ordinary requests like 'explain this codebase' may result in creating or updating ONBOARDING.md, and only use the optional sharing step if you are comfortable uploading that generated document.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly directs the agent to write or refresh `ONBOARDING.md` in the repository, but it does not require an explicit confirmation step or a prominent warning that repository files will be modified. In environments where users expect analysis-only behavior, this can cause unintended file changes, noisy diffs, or accidental commits of AI-generated content.

Static analysis

No suspicious patterns detected.