ClawHub
Back to skill

Security audit

execute-tdd-spec

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent TDD workflow helper for implementing an approved spec, with one notable usability caveat: it forces Portuguese user-facing communication.

Install this if you want an agent to execute approved spec-driven TDD work in a repository. Be aware it will communicate progress and questions in Portuguese by default, and it will continue through approved spec slices without asking for approval between each slice.

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)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The skill explicitly mandates that all user-facing questions and explanations be in Portuguese (pt-BR), regardless of the user's language or preferences. This can override user intent, reduce transparency, and create safety/comprehension risks if the user cannot accurately understand implementation status, test results, or warnings.

Static analysis

No suspicious patterns detected.