clickup-api

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is designed to ingest and process external data from ClickUp chat channels.
  • Ingestion points: The skill references fetching message history via clickup_get_chat_channel_messages to identify existing DM channels (SKILL.md).
  • Boundary markers: The instructions do not define any delimiters or boundary markers to differentiate between user instructions and ingested chat content.
  • Capability inventory: The skill has the capability to send messages (POST /chat/channels/{id}/messages), create new direct message channels (POST /chat/channels/direct_message), and reply to existing threads (POST /messages/{message_id}/replies).
  • Sanitization: There are no documented procedures for sanitizing, escaping, or validating the content of external chat messages before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 05:43 AM
Security Audit — agent-trust-hub — clickup-api