skills/vm0-ai/vm0-skills/clickup/Gen Agent Trust Hub

clickup

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate instructions for interacting with ClickUp's API.
  • [COMMAND_EXECUTION]: Uses standard curl and jq commands for API interaction and response processing.
  • [EXTERNAL_DOWNLOADS]: Network operations are directed at the official ClickUp API domain (api.clickup.com), which is a well-known and trusted service.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection (Category 8) by reading external data like task descriptions and comments. Ingestion points: ClickUp API results processed in SKILL.md. Boundary markers: Absent. Capability inventory: curl and jq subprocess calls, and file-writes to /tmp. Sanitization: Absent. No malicious instructions were found in the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 04:43 PM