ClawHub
Back to skill

Security audit

AI大模型专家｜Agent Harness 工程｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-HIVE workflow helper that plans agent-harness work, queries model availability, and writes local plan records with clear confirmation gates for paid or irreversible actions.

Install this if you intentionally want AI-HIVE-oriented Agent Harness planning. Keep the AI_HIVE_API_KEY in a secure environment variable, review generated plan files before sharing them, and require explicit confirmation before any paid, batch, external publishing, deletion, or permission-changing action.

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
90% confidence
Finding
The skill embeds runnable command examples and explicitly relies on environment variables, local files, and network access, but it does not declare corresponding permissions. This creates a mismatch between what the skill appears allowed to do and what it instructs an agent or user to perform, increasing the risk of unintended data access, outbound requests, or file writes without proper review and consent boundaries.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger list includes very broad terms such as 'API', 'MCP', 'Agent', '教程', and '自动化', which can cause the skill to activate for many unrelated requests. Over-broad invocation increases the chance that users are routed into workflows involving model selection, pricing queries, file generation, or external platform guidance when they did not intend to use this vendor-specific skill.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The manifest sets allow_implicit_invocation: true without any visible trigger scoping or user-confirmation guardrails, so the skill may activate in broader contexts than intended. Because this skill is positioned to plan, route tasks through AI-HIVE, and save task results, ambiguous invocation can lead to unintended execution, unexpected external calls, or accidental persistence of user/task data.

Static analysis

No suspicious patterns detected.