raindrop-api

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read or ask for the user's Raindrop API token (from conversation context or AskUserQuestion) and then use it in Authorization headers/curl requests, which could require the LLM to include secret values verbatim in generated commands.

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to fetch and read user bookmarks, highlights and parsed webpage data from the public Raindrop.io API (e.g., GET /raindrops/{collectionId}, GET /raindrop/{id}, /highlights, and /import/url/parse), which returns user-generated links, titles, excerpts and page content from arbitrary websites — untrusted third‑party content that the agent is expected to read and interpret.