clickupfy-dev

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external ClickUp tasks and comments.
  • Ingestion points: External content is retrieved using commands like clickupfy task get <id> --json, clickupfy_task_get, and clickupfy comment list (found in SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the fetched ClickUp content.
  • Capability inventory: The agent has the capability to create, update, and delete tasks, manage checklists, and record time entries across scripts.
  • Sanitization: No sanitization or filtering mechanisms are described for the external content before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a variety of shell commands via the clickupfy CLI tool to perform workspace operations, task management, and time tracking.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 08:20 PM
Security Audit — agent-trust-hub — clickupfy-dev