plugin-creation

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly describes and instructs using an MCP (“Skill Seeker MCP”) to scrape external documentation sites (references/03-skills/creation-approaches.md shows commands like mcp__skill-seeker__scrape_docs --config ... and URLs such as https://docs.example.com) and also describes MCP HTTP transports and cloning public repos, meaning the agent will ingest and act on arbitrary public third‑party content that can influence downstream tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 12:30 AM