ClawHub
Back to skill

Security audit

MBTA Transit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MBTA transit lookup tool that only queries public MBTA API data, with an optional API key for rate limits.

Installing this skill mainly gives the agent a convenience script for MBTA lookups. Be aware that queries are sent to the MBTA API, and if you set MBTA_API_KEY it will be included in those API requests for rate limiting.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · SKILL.md (reported line 119)May include surrounding context.

md
## Tips for the AI Agent

1. **Always use stop IDs over names** when you have them — more reliable
2. **Search for stop IDs first** if you only have a station name: `stops "Name"`
3. **Parent station IDs** (e.g., `place-sstat`) cover all platforms — use these for departures
4. **Predictions may be empty** at night or when service isn't running

Static analysis

No suspicious patterns detected.