Back to skill

Security audit

salon-booking-messages

Security checks for vulnerabilities and agentic risk

Overview

The bundled workflow has limited local access, although its script checks message fields instead of producing the promised drafts.

Expect a validation report, not finished customer messages. Review drafts and salon policies before sending. Choose an output folder where replacing booking-message.md is acceptable. The optional unsigned Windows app is unnecessary for the Python workflow and requires a separate trust decision.

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
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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code requires message content to be supplied in the input. It only counts characters, flags missing or over-limit fields, and appends fixed guardrails. It contains no message-generation logic and does not include the supplied message text in its output. This is a material functional mismatch, not an undeclared security-sensitive capability. Local input reading and report writing are ordinary supporting implementation details.

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.

The skill produces a field-validation report rather than drafting salon booking messages.

Low
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises confirmation, reminder, and reschedule message drafts. At L091–L103, the code only checks supplied fields for presence and character count; L105–L115 then writes those results and generic guardrails to booking-message.md, without generating or including any actual message text.

Content

No source excerpt is available for this finding.