skills/clawlink-hq/skills/onedrive/Gen Agent Trust Hub

onedrive

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and run the @useclawlink/cli package from the NPM registry. This package is the official tool provided by the vendor for interacting with their service.
  • [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands via the @useclawlink/cli to perform actions such as logging in, connecting to OneDrive, and managing files.
  • [DATA_EXFILTRATION]: The skill manages authentication by storing credentials locally at ~/.clawlink/credentials.json. This is a standard procedure for CLI-based authentication tools to maintain session state.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external data such as file names and metadata from a user's OneDrive account. While this represents a potential surface for indirect prompt injection, it is the intended functionality of a file management skill.
  • Ingestion points: SKILL.md (via actions like one_drive_search_items, one_drive_list_folder_children, and one_drive_get_item)
  • Boundary markers: Absent
  • Capability inventory: SKILL.md (includes capabilities for file upload, download, move, copy, and deletion)
  • Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — onedrive