ClawHub
Back to skill

Security audit

Codebase Explorer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-oriented codebase onboarding helper with no bundled code, network behavior, credentials, or hidden persistence.

Install this if you want an agent to inspect repository structure and produce onboarding notes. Review any generated CLAUDE.md before keeping it, since project instructions can influence 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases include broad natural-language requests such as "understand this codebase," "analyze this repo," and "walk me through," which can overlap with ordinary conversation and cause the skill to activate when the user did not explicitly intend to invoke it. Unintended activation is risky because the skill is designed to perform broad repository reconnaissance and generate project instructions, potentially expanding scope, consuming resources, or surfacing sensitive structural details unnecessarily.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The "When to Use" section mixes concrete requests with general-purpose phrasing, but it does not define strict invocation boundaries or exclusions. That ambiguity can cause over-triggering in adjacent contexts, leading the agent to begin systematic codebase analysis when a user only wanted a narrow explanation or casual walkthrough.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.