ClawHub
Back to skill

Security audit

Writing Plans

Security checks for vulnerabilities and agentic risk

Overview

This is a planning helper with messy metadata and mixed-language instructions, but it does not show hidden, destructive, or data-stealing behavior.

Before installing, be aware that the manifest description should be cleaned up and some generic compliance text is in Indonesian. The skill is intended to create plan files and may recommend subagent-based execution, so only proceed with execution options you explicitly want.

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The description on L003 contains broken text and broad trigger language such as "step task?" and "Aktif untuk tugas terkait writing-plans," which does not clearly define when the skill should or should not activate. Although the body later provides better guidance, the manifest-facing description is still ambiguous and could cause unintended invocation in systems that rely on frontmatter metadata.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
Large portions of the skill, including the frontmatter description and compliance-layer instructions, are written in Indonesian, which imposes a language choice on users and downstream agents. The file does not state that the locale is intentionally restricted or provide an opt-in or alternative language, so this is a natural-language policy concern.

Static analysis

No suspicious patterns detected.