ClawHub
Back to skill

Security audit

Conference Schedule Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local conference schedule helper with overstated documentation but no hidden data access, persistence, network use, or destructive behavior.

Reasonable to install if you want a lightweight local JSON-based conference scheduler. Review the documentation expectations first, because several advertised features appear illustrative or missing from the bundled script.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 related to conference schedule optimization, so the high-level domain matches the description. However, the declared description overstates what the implementation actually does. The code only performs basic session ranking using interest keyword matches in titles/topics, honors must-attend sessions, and avoids sessions with the same start time. There is no logic for networking optimization, career development balancing, travel/buffer time between presentations, or richer multi-objective personalization. Thus the description is materially broader than the actual implemented behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The summary text is broad enough to trigger on generic planning or scheduling requests that are not specific to conference optimization, which can cause the agent to invoke this skill outside its intended scope. Over-broad routing increases the chance of context hijacking or inappropriate delegation, especially when the skill may receive unrelated user data or influence decisions it was not designed to handle.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.