swiftscholar-skill

Integrates the SwiftScholar HTTP API for searching, submitting, and analyzing academic papers. Use when the user wants to search literature, submit PDFs/URLs for parsing, retrieve analyses, manage favorites, or inspect SwiftScholar account usage programmatically.

Before installing or enabling this skill: 1) Recognize the SKILL.md requires a SwiftScholar API key (Authorization: Bearer <SWIFTSCHOLAR_API_KEY>), but the skill metadata does not declare that requirement — confirm with the skill author or registry how/where the key must be provided. 2) Do not paste secrets into chat; place the API key only into a secured execution environment (env var or tool config) the agent will use. 3) Be cautious about uploading sensitive PDFs: the skill supports pdfBase64 or multipart uploads that will send file contents to swiftscholar.net. Prefer submitting public URLs or removing sensitive information before upload. 4) Verify the API base URL (https://www.swiftscholar.net) and review SwiftScholar's privacy/retention policy if you will send user data. 5) If you cannot confirm where the API key is stored or how the agent obtains it, treat the skill as untrusted and do not provide credentials.

Type: OpenClaw Skill Name: swiftscholar-skill Version: 1.0.0 The OpenClaw AgentSkills skill bundle for 'swiftscholar-skill' is benign. The `SKILL.md` provides clear, well-structured instructions for an AI agent to interact with the SwiftScholar HTTP API at `https://www.swiftscholar.net` for academic paper management. It explicitly instructs the agent not to expose the `SWIFTSCHOLAR_API_KEY` in natural language responses, which is a positive security measure. There is no evidence of prompt injection attempts, unauthorized data exfiltration beyond the stated API interaction, malicious command execution, or persistence mechanisms. All files consistently describe the intended functionality without any hidden or harmful directives.