qa-clickup-integration

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources and interpolates them into ClickUp API requests, creating a surface for indirect prompt injection.
  • Ingestion points: The skill processes data from qa-bug-ticket-creator, qa-task-creator, and direct user input to generate ClickUp tasks as described in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat external data as untrusted or to ignore instructions embedded within task fields.
  • Capability inventory: The skill has the capability to perform network operations (POST, PUT, GET) to the ClickUp API and upload attachments as detailed in references/api-patterns.md.
  • Sanitization: No evidence of sanitization or validation of the ingested data is present.
  • [SAFE]: Communicates with ClickUp, a well-known project management service, via its official REST API (https://api.clickup.com/api/v2).
  • [SAFE]: Recommends storing sensitive API tokens in a .env file, which is a standard industry practice for secure secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:38 PM
Security Audit — agent-trust-hub — qa-clickup-integration