readwise-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly tells the agent to ask the user for their Readwise access token and then run a CLI command embedding that token verbatim (readwise login-with-token ), which requires handling and outputting a secret value directly.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly shows commands that save and scrape arbitrary public URLs (reader-create-document --url "...") and retrieve full document content for reading/processing (reader-get-document-details, reader-list-documents with html_content/summary), meaning the agent ingests untrusted third-party web content as part of its workflow and that content could influence subsequent actions.