The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in the provided skill.
[PROMPT_INJECTION]: The skill does not contain instructions that attempt to override agent behavior or bypass safety guidelines.
[DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were found; the skill demonstrates best practices for managing web data safely.
[REMOTE_CODE_EXECUTION]: The skill covers JavaScript execution using native WebKit APIs and provides clear guidance on preventing injection attacks through isolated content worlds and safe argument passing.
[COMMAND_EXECUTION]: No unauthorized shell command execution or privilege escalation patterns were identified.
[EXTERNAL_DOWNLOADS]: No suspicious remote dependencies or unverified code downloads were detected.

webkit-integration