ClawHub
Back to skill

Security audit

AI大模型专家｜柏拉图AI_API中转站 (api.bltcy.top) 替代方案｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a cautious migration-planning aid that creates a local JSON plan and does not contain hidden network, credential-reading, or destructive automation.

Use this skill for planning, not for storing or pasting real API keys. Run the helper only in a workspace where creating the output JSON is acceptable, verify current platform terms and prices yourself, and require explicit owner approval before any production key rotation or tenant migration.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill instructs users to run a local script that writes an output file (`secret-rotation-plan.json`), yet no explicit permission declaration is present. Undeclared file-write capability is dangerous because it weakens user awareness and platform enforcement boundaries, making it easier for a skill to modify the local workspace unexpectedly.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill can be invoked implicitly with no trigger constraints, even though it is designed to handle sensitive operations involving API keys, tenant switching, revocation, and production credential workflows. That creates a real risk of the agent auto-selecting this skill in loosely related conversations and producing guidance or actions around secrets, access scopes, or migration steps without sufficiently explicit user intent or safety gating.

Static analysis

No suspicious patterns detected.