Back to skill

Security audit

Widespread Verified Work

Security checks for vulnerabilities and agentic risk

Overview

The scanners report an unpinned `uvx widespread-mcp` package command, so the skill is rated suspicious because a future package release could change and run with local permissions; the scan does not show that the package is malicious.

Consider waiting until the MCP package is pinned to a reviewed version or verified artifact before installing. If you proceed, consider the scanner’s concern that package code could run with local permissions and affect the signing key or paid-work identity.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

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

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The unpinned uvx widespread-mcp command can download and execute a changing package release, allowing a compromised future release to run with the agent's local permissions. This is particularly consequential because the MCP server manages the agent's signing key and paid-work identity; malicious package code could steal the key or sign unauthorized operations despite the documentation's claim that keys never leave the client. There is no evidence here that the package itself is malicious.

Content

No source excerpt is available for this finding.