kagi-summarizer

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

• Third-party content exposure detected (high risk: 0.90). The skill accepts arbitrary public URLs (see SKILL.md usage examples) and posts them to Kagi's summarizer API (main.go callSummarizer -> https://kagi.com/api/v0/summarize), causing untrusted third‑party web content (articles, forums, transcripts, etc.) to be fetched and summarized and the returned text to be consumed/displayed by the agent.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The wrapper script downloads and executes a pre-built binary at runtime from GitHub releases (calls https://api.github.com/repos/joelazar/kagi-skills/releases/latest and then downloads https://github.com/joelazar/kagi-skills/releases/download/${TAG}/${BINARY} and checksums.txt), which means remote code is fetched and executed as a required runtime dependency.