Back to skill

Security audit

frame-security-scan

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a coherent security-scanning workflow with user approval required for installation, code sharing, and applying fixes.

The advisory scanner's two reports concern the same unpinned MCP command; the artifacts support treating this as an installation precaution. Pin reviewed package versions, approve the AI endpoint before sharing repository code, and review proposed changes with backups available. A clean scan does not prove code is secure.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

MCP server referenced without pinned version: 'uvx frame-mcp'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The MCP registration command uses uvx frame-mcp without a version constraint, allowing a newly resolved release to execute with the user's privileges. A compromised package release could access source code, credentials, or writable files; the security-scanning context makes access to sensitive repositories particularly likely, although nothing here establishes malicious author intent.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'uvx frame-mcp'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The standalone uvx frame-mcp recommendation likewise executes a package without selecting a reviewed version, creating exposure to malicious or compromised future releases. An MCP server running in a developer environment could access sensitive code and credentials; this is a second occurrence of the same supply-chain weakness, not a separate attack mechanism.

Content

No source excerpt is available for this finding.