The Agent Skills Directory

SAFE (SAFE): No security issues detected. The skill's functionality is limited to reading local text and providing summaries to the user. There are no indications of prompt injection, data exfiltration, or unauthorized command execution. No hardcoded credentials or sensitive file paths are accessed. The skill does not perform any network operations or external downloads. While the skill processes untrusted input (the novels it summarizes), the absence of high-privilege tools like shell execution or network requests eliminates the risk of harmful indirect prompt injection.

novel-summarizer