Back to skill

Security audit

grocery-flow-architect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local grocery-list routing helper with disclosed, proportionate file use and no evidence of hidden network, credential, destructive, or persistence behavior.

Install only if you are comfortable with a local script reading the shopping-list file you give it and saving grocery maps, learned zones, and staple timing under ~/.grocery_flow/. Use normal store names and list paths you intend to share with the tool.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill explicitly describes persistent local storage in ~/.grocery_flow/ and invokes a Python CLI that reads list files and writes per-store JSON, yet it does not declare any tool scope or permissions boundary. That mismatch can cause an agent or user to grant broader filesystem access than expected, increasing the risk of unintended reads or writes if the implementation is modified, misused, or interpreted too permissively.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.