skills/timsonner/agent-skills/rclone/Gen Agent Trust Hub

rclone

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides command syntax for the rclone utility, enabling the agent to perform filesystem operations and network-based file transfers.- [DATA_EXFILTRATION]: Documentation includes examples for transferring files to external cloud storage (e.g., S3) and remote shares, creating a path for moving data outside the local environment.- [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The agent interacts with external data by listing files on remote systems via rclone ls (SKILL.md).
  • Boundary markers: No delimiters or instructions are provided to the agent to distinguish between trusted instructions and data retrieved from external remotes.
  • Capability inventory: The skill uses the rclone CLI, which possesses extensive capabilities for network communication and filesystem access (SKILL.md).
  • Sanitization: The skill does not specify any sanitization or validation steps for data or metadata (like filenames) received from remote storage providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 02:39 AM
Security Audit — agent-trust-hub — rclone