Security audit
Security checks for vulnerabilities and agentic risk
This Readwise skill is a straightforward, disclosed integration for reading highlights and Reader documents, with a user-invoked URL save command.
Install this only if you are comfortable giving the skill access to your Readwise account data. Treat returned highlights, notes, saved article metadata, and partial content as potentially sensitive, and use the save command only for URLs you intend to add to Reader.
The skill description says it provides access to Readwise highlights and saved articles, but the CLI also supports a save command that creates new Reader entries from arbitrary URLs. This is a scope-expansion issue: users or calling agents may grant the skill read-oriented access while unknowingly enabling write actions against the connected Readwise account.
The get path returns full document details including content, notes, and highlights, which goes beyond a narrow interpretation of 'highlights and saved articles' access. While this is not code execution or direct token leakage, it increases data exposure and can surprise users who expect more limited retrieval behavior.
The skill instructs users to configure a persistent Readwise API token and then use commands that fetch, search, export, and save data against external Readwise/Reader services, but it does not clearly warn that the user's highlights, saved articles, queries, and submitted URLs will be transmitted to that third-party service. This is primarily a transparency and informed-consent issue rather than an exploit primitive, but it can expose sensitive reading history or notes if users do not realize external data transfer is occurring.
No suspicious patterns detected.
