ClawHub
Back to skill

Security audit

Repo Tour

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed repo-documentation generator that reads project files and creates one local HTML walkthrough, with no hidden execution or persistence found.

Before installing, understand that generated tours may contain real source code, internal file paths, and architecture details. Use it on repositories you are comfortable summarizing locally, choose the output path deliberately, and review the HTML before sharing it outside the project.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · README.md (reported line 14)May include surrounding context.

md
Use this skill for explicit requests to create a Code Decoded course, repo tour, onboarding walkthrough, or stakeholder explanation. It should not trigger for ordinary code review, refactoring, or debugging.

The agent reads repository files and writes one self-contained HTML file. Confirm the output path before generation, avoid overwriting existing files without approval, and review the HTML before sharing because it may include real code snippets, private paths, and architecture details.

## What it generates

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The invocation examples are broad enough that an agent may match on generic requests like onboarding material or explaining a repo, causing the skill to activate outside a narrowly scoped, explicit command. Because the skill reads repository contents and generates a shareable HTML artifact that may include code snippets, internal paths, and architecture details, accidental activation can lead to unintended data exposure or unnecessary file generation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The example document structure specifies <html lang="en">, which imposes an English locale in natural-language guidance. This file does not offer a language choice or explain why English is required, so it conflicts with the policy against forcing a specific language or locale without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.