ClawHub
Back to skill

Security audit

US Business SOP Builder

Security checks for vulnerabilities and agentic risk

Overview

The skill provides SOP-writing guidance and a local checker, with no hidden access, automatic downloads, or background activity.

Review the SOP yourself because the checker cannot confirm each step has an owner or deadline. Use a dedicated output folder because an existing lint-report.md is overwritten. The optional unsigned Windows app is separate from this review and should be evaluated independently.

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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Although the checks are relevant to SOP documentation and could support a broader builder, the supplied executable only validates existing text and produces lint-report.md. Its primary behavior therefore materially differs from the declared transformation capability. Local file reading and report writing are ordinary supporting operations; no unrelated resource access or external communication is shown.

Content

No source excerpt is available for this finding.

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

Static analysis

No suspicious patterns detected.