ClawHub
Back to skill

Security audit

Rework Repair Plan

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed report-generation aid for rework and repair planning, with only minor caution around local file output and a missing referenced helper script.

Before installing, understand that the skill may produce local report files containing customer, product, and quality details. Confirm where files will be written, avoid overwriting existing documents, and do not run any scripts/build_report.py unless it is a trusted, intended helper from the skill package or your own reviewed tooling.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly states it will write TXT and MD files into the user's working directory, but it does not warn about file creation, possible overwrite behavior, or require explicit user confirmation before doing so. Even though the files appear to be normal report outputs, silent filesystem writes can surprise users, overwrite existing documents with similar names, or leak sensitive quality/customer data into unintended locations.

Content

No source excerpt is available for this finding.