Back to skill

Security audit

Salai MCP (Beta)

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Salai grocery MCP skill that discloses its API-key requirement and cart-management powers, with no evidence of hidden code, persistence, or unrelated behavior.

Install only if you intend to connect Codex to your Salai account. Treat the Salai API key as a secret, and ask the agent to confirm before adding, updating, removing, or deleting cart items, especially for delete_cart or bulk updates.

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
  • 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)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly exposes state-changing cart operations, including item updates and cart deletion, but provides no guidance to require explicit user confirmation before destructive or purchasing-adjacent actions. In an agent setting, this increases the risk of unintended modifications from ambiguous prompts, prompt injection in surrounding context, or mistaken tool selection, causing unauthorized cart changes or deletion of a user's shopping state.

Static analysis

No suspicious patterns detected.