Back to skill

Security audit

Travel Planning

Security checks for vulnerabilities and agentic risk

Overview

The skill’s travel-planning workflow is coherent and proportionate, with routine privacy and dependency-installation considerations.

Travel details included in prompts go to CellCog; share only what is needed, especially for accessibility or other personal constraints. Review the separate CellCog dependency and prefer reviewed package versions before setup. Its implementation and data-retention practices were outside the supplied artifact.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Travel prompts are sent to CellCog without a privacy warning about sharing personal travel information with a third-party service.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The workflow instructs the agent to submit the task prompt to CellCog through create_chat. The skill encourages including travel dates, budgets, traveler details, and accessibility constraints, but never warns that these details will be transmitted to an external service.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The installation command invokes an unpinned npm CLI through npx skills, allowing the code executed during setup to change without review. A compromised upstream release could execute with the installing user's permissions and access local files or credentials; however, the static finding incorrectly describes this CLI as an MCP server.

Content

No source excerpt is available for this finding.