ClawHub
Back to skill

Security audit

长期目标管理

Security checks for vulnerabilities and agentic risk

Overview

This skill persistently manages a user-visible goal.md file for long-running work, and the file access it requests is disclosed and aligned with that purpose.

Install this only if you want the agent to maintain a persistent goal.md in your workspace for long-running work. Review the chosen goal.md path and avoid storing secrets or sensitive private details in it unless you intend that information to persist across sessions.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill explicitly instructs the agent to read and write workspace files, including creating and continuously updating a persistent `goal.md`, but it declares no permissions. That mismatch is dangerous because it can bypass user/operator expectations and allow persistent state modification across sessions without clear capability disclosure or gating.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger conditions are very broad, including generic phrases like long-term, ongoing, iterative, multi-round work, or requests to continue from prior materials. This can cause the skill to activate during ordinary conversations and then start reading or writing persistent project state, increasing the chance of unintended file access, state corruption, or hidden prompt steering across sessions.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The default prompt automatically instructs use of $long-goal in broad natural language without explicit activation boundaries or user confirmation. In a system that manages persistent goal.md state across turns and sessions, this can cause unintended invocation, persistence of sensitive context, or inappropriate carryover of prior session material when a user did not clearly intend to enter long-term memory workflow.

Static analysis

No suspicious patterns detected.