ClawHub
Back to skill

Security audit

salon-booking-messages

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill has limited local access and no hidden external actions, but its script checks message fields instead of drafting messages.

Expect to draft and review the actual messages yourself or through your agent; the script only checks fields and its template needs adjustment. Choose an output folder where replacing booking-message.md is acceptable. The optional unsigned Windows app is unnecessary for this workflow and requires a separate security assessment.

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
99% confidence
Finding

The primary implemented behavior is message-field validation and reporting, materially different from drafting booking messages. The output contains field lengths, missing-field notices, and static guardrails rather than confirmations, reminders, or rescheduling messages. Local file reads and report writes are ordinary supporting implementation details; there is no evidence of unrelated resource access or hidden external actions.

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.