The Agent Skills Directory

[SAFE]: The skill follows security best practices for handling external data. It explicitly instructs the agent to use the --wrap-untrusted flag when reading Google Drive content, which is a key mitigation strategy against indirect prompt injection from untrusted document data. Furthermore, it incorporates operational safety markers like --readonly, --dry-run, and --no-input to prevent accidental or unauthorized modifications to the user's data. No malicious patterns such as obfuscation, unauthorized data exfiltration, or remote code execution were detected.

gog-drive