ClawHub
Back to skill

Security audit

Technical Doc Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill generates documentation from a codebase and its file-reading and documentation-writing behavior is coherent with that purpose.

Before installing, expect the skill to read selected project files and write generated documentation. Run it on a working branch, prefer an output directory when possible, and review any docs/ or README changes before committing.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs saving generated documentation into output/docs/ or docs/ and even copying a README to the project root, but it does not clearly warn the user up front that running the skill will modify the repository. In an agentic context, silent filesystem writes can overwrite existing documentation, create noisy diffs, or alter tracked files in a client repo without informed consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.