rclone
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes shell script examples and mount recipes that use the
rclonecommand. These are standard for the tool's intended use and are accompanied by strict safety guidelines, such as using--dry-runand--backup-dirto prevent accidental data loss. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external data sources such as command logs, configuration files, and provider quota pages. While this creates a surface for processing potentially untrusted content, the skill provides explicit safety directives requiring the agent to refuse requests for sensitive credentials and to verify operation types (e.g., sync vs. copy) before providing advice.
Audit Metadata