ClawHub
Back to skill

Security audit

migration-risk-quick-scan

Security checks for vulnerabilities and agentic risk

Overview

This local migration checker fits its stated purpose, with precautions needed for saved reports and sensitive SQL snippets.

Use a specific migration directory and keep the default terminal output, or choose a new report filename: --out can overwrite existing files. Reports may contain sensitive SQL values. Treat a clean result as a limited pattern check, not deployment approval.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The scanner writes files despite its explicit "Never modifies files" guarantee.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The optional --out argument reaches Path.write_text without overwrite protection, contradicting the unconditional claim that the scanner never modifies files. An existing migration or another writable file can be truncated and replaced with JSON if selected as the output path; the explicit, documented opt-in limits exposure but does not prevent accidental data loss.

Content

No source excerpt is available for this finding.