ClawHub
Back to skill

Security audit

Multi City Activation Planner

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign with high confidence: its reported behavior aligns with its planning purpose, though one finding notes that itinerary details may be sent to TempGuru or saved without advance disclosure.

The scan covered all reported components and completed successfully. Before installing, consider whether you are comfortable sharing relevant city, date, staffing, and event details with TempGuru, and avoid including sensitive information in special requirements.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The planning workflow sends itinerary details to TempGuru and may save a city-leg plan without first disclosing that data transfer to the buyer.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow directs the agent to call the external planning service for every city and conditionally save a plan containing buyer-provided event information. Although the service is identified and the later form submission is buyer-operated, the skill does not instruct the agent to warn that itinerary details are transmitted—and may be stored—during the earlier planning stage.

Content

No source excerpt is available for this finding.