Back to skill

Security audit

MPP Router — Service Discovery

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly describes a paid MPP Router discovery and payment handoff flow, with visible mainnet-payment warnings and confirmation gating.

Install this only if you want agents to discover and use paid MPP Router services. Review prompts carefully when a task could be handled without paid routing, and rely on the payment confirmation step before any Stellar mainnet spend.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger examples in the frontmatter are broad enough to match generic requests like summarization, search, or 'find a service' even when the user may not intend to use a paid Stellar-backed router. In this skill's context, mistaken activation is more dangerous than usual because it can steer the agent toward live catalog lookup and potentially real-money mainnet payment flows.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The 'When to trigger' section relies mostly on examples and a broad name-match rule, without clearly excluding adjacent intents like ordinary web search, scraping, or summarization. This ambiguity can cause over-activation, and in a payment-enabled skill that increases the chance of unnecessary service discovery, confusing user experience, or escalation into a payment flow the user did not intend.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.