keyapi-pinterest-analysis
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly calls the KeyAPI MCP Pinterest endpoint (https://mcp.keyapi.ai/pinterest/mcp) to fetch public Pinterest user/pin/board/follower data (see SKILL.md Workflow and scripts/run.js where client.callTool parses responses and the numeric userid from get_user_information is used to drive get_followers_detail/get_following_detail), so it ingests untrusted, user-generated third‑party content at runtime that directly influences subsequent tool calls and analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata