The Agent Skills Directory

[SAFE]: No malicious patterns detected. The skill automates the drafting of legal status request emails by reading local case files and writing markdown drafts.
[DATA_EXPOSURE_&_EXFILTRATION]: The skill accesses sensitive legal data (matter history, budgets, and contact information), but this access is limited to the local filesystem (~/.claude/plugins/config/claude-for-legal-zh/litigation-legal/). There are no network operations (curl, wget, fetch) or patterns indicating data exfiltration to external domains.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from local files (matter.md, history.md) to populate templates. While this represents a data ingestion surface, the risk is mitigated because the data sources are local configuration files, and the skill lacks dangerous capabilities such as shell execution or automated network requests. The skill also explicitly instructs the user to review all drafts for accuracy and confidentiality before sending.
[REMOTE_CODE_EXECUTION]: No external dependencies, package installations, or remote script downloads are performed.
[OBFUSCATION]: No obfuscated content, Base64 strings, or hidden characters were found in the skill instructions.

oc-status