ClawHub
Back to skill

Security audit

write-goal

Security checks for vulnerabilities and agentic risk

Overview

This is a goal-writing helper that is limited to structured planning instructions and does not ship code, persistence, credential access, or hidden data flows.

Before installing, be aware that this skill may activate for broad goal-planning or vague decomposition requests. Its behavior is otherwise disclosed: it helps draft goals and may use available goal-management tools to create or refine goals according to the user's stated objective and budget.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description says to use the skill when the user asks for help 'writing, refining, or improving a goal' or when a request 'is vague and would benefit from structured decomposition before execution.' This scope is broad and lacks clear exclusion conditions, which could cause the skill to activate for many ordinary planning or clarification requests beyond the intended command-style triggers.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.