ClawHub
Back to skill

Security audit

tdd-spec

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed SPEC-driven TDD workflow skill with no hidden code, persistence, credential handling, or unrelated authority.

Install this skill if you want a disciplined SPEC-first TDD workflow and are comfortable with user-facing responses in Portuguese. Review the referenced slash-command dependencies in your environment if you rely on `/grill-me-with-spec` or `/qa-analyst`, but this package itself is Markdown guidance only.

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 (2)

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The description states that all user-facing questions and recommendations must be in Portuguese (pt-BR). This is a natural-language locale restriction that applies unconditionally and does not provide an opt-in or alternative language choice.

Natural-Language Policy Violations

Medium
Confidence
98% confidence
Finding
This line imposes a fixed language policy for user-facing communication. Under the policy, forcing a specific language without user choice or a clearly justified documented constraint is a violation.

Static analysis

No suspicious patterns detected.