readwise-second-brain-sync

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs using readwise login-with-token <token> and refers to obtaining the access token URL, which encourages embedding a secret API token directly on the command line (verbatim), an insecure exfiltration pattern.

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text from Readwise (public/third-party user content) is fetched at runtime via the readwise CLI (reader-get-document-details / readwise-list-highlights) and then rendered into markdown written to raw/, which /second-brain-ingest will later read—so the LLM context can be influenced indirectly by that outsider text.