Security audit
Security checks for vulnerabilities and agentic risk
This skill is a small URL-to-Markdown helper that openly uses Jina.ai Reader, with privacy caveats but no hidden persistence, credential access, or destructive behavior.
Install only if you are comfortable sending the requested URL to Jina.ai Reader. Do not use it for confidential documents, private intranet pages, signed URLs, URLs containing access tokens, or content where paywall or site terms matter.
The skill performs network access to fetch remote content but does not declare any explicit tool scope or permissions boundary. This weakens reviewability and policy enforcement, increasing the chance the skill is invoked in contexts where users or orchestrators are not clearly informed that external network access will occur.
The skill routes user-supplied URLs and retrieves page contents through the third-party Jina.ai Reader service, yet the description does not warn users that their requested targets and extracted content leave the local environment. This creates a privacy and data-handling risk, especially if users pass sensitive, internal, authenticated, or proprietary URLs/content assuming the skill behaves like a direct local fetcher.
No suspicious patterns detected.
