agentform

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). This skill config declares an MCP GitHub server (server "github" using @modelcontextprotocol/server-github) and capabilities such as get_pr that read pull request content from GitHub—public, user-generated data the agent is expected to read and interpret as part of workflows.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:35 PM