ClawHub
Back to skill

Security audit

Codebase Onboarder

Security checks for vulnerabilities and agentic risk

Overview

This skill reads a repository to generate onboarding documentation, and its file inspection behavior matches that purpose.

Install this for repositories you intentionally want summarized. Review generated onboarding output before sharing it, especially configuration and environment sections, and redact any real credentials or sensitive internal infrastructure details if they appear.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases are very broad and map to common, everyday requests like 'help me understand this codebase' or 'document this project', which can cause the skill to activate in contexts the user did not explicitly intend. That increases the chance the agent performs wide repo inspection and summarizes sensitive project structure or code details without sufficiently clear user consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly directs inspection of environment-variable usage and '.env' template files and asks the agent to document which variables are secrets, but it provides no guardrails against reproducing sensitive values or over-collecting configuration details. In a real repository, this can lead to exposure of secret names, internal service topology, authentication configuration, or accidentally checked-in credentials in the generated onboarding output.

Static analysis

No suspicious patterns detected.