Back to skill

Security audit

appointment-scheduling-rules

Security checks for vulnerabilities and agentic risk

Overview

The skill needs review because its advertised privacy and compliance checker misses the warning phrases it is designed to detect.

Use this only to prepare drafts. Have the checker corrected and tested before relying on its results, and independently review privacy, consent, and legal requirements before sending anything. Keep real customer details out of shared templates. The optional unsigned Windows app is unnecessary for the bundled workflow and requires separate assessment.

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 (2)

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 documented compliance checks are not executed: regex rules are treated as literal substrings.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The checker tests whether each entire regex string occurs literally in the input instead of evaluating it, so ordinary text such as 'no opt out' or 'test result' produces no flag. Because this skill generates compliance-oriented reminder copy, the resulting 'No flags' report can create false assurance and allow privacy-sensitive content or potentially noncompliant messaging to pass review; there is no evidence that this defect is intentional.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.