ClawHub
Back to skill

Security audit

rec-league-scheduler

Security checks for vulnerabilities and agentic risk

Overview

This is a local recreational league scheduling helper that stores roster and match data in a local JSON file and does not show hidden, networked, privileged, or destructive behavior.

Before installing, understand that this tool keeps league data locally in league.json, including player names, absences, scores, byes, and pair history. Use the --db option carefully because it can write to a path you provide. Treat the fairness and call-up features as lightweight scheduling aids, not a full league-management system.

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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The code is strongly aligned with the general declared purpose: it is clearly a recreational league scheduling and administration tool, and most listed features are present in some form. However, the description overstates or misstates several capabilities. The biggest gap is that the match-night logic does not schedule from the generated round-robin fixtures; instead it creates fresh pairings using a greedy unmet-pair/skill-balance heuristic. Also, the claimed availability registry and sub/call-up handling are only rudimentarily represented by absence records and a suggestion list, not a true registry or substitute workflow. Finally, the fairness audit is approximate and tied to recorded results/bye history rather than a comprehensive accounting of all court time. These are material description-versus-behavior differences, though the primary purpose remains the same.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

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.