Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/clickup-core-workflow-a/Gen Agent Trust Hub

clickup-core-workflow-a

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from ClickUp tasks, which are external sources that could contain malicious instructions intended to influence agent behavior.
  • Ingestion points: External data is retrieved from ClickUp via the getTasks and searchTasks functions described in SKILL.md.
  • Boundary markers: While the instructions mandate validating the intended state and actor authorization, the provided code examples do not implement explicit delimiters or boundary markers to isolate untrusted task content.
  • Capability inventory: The skill requests access to Bash(curl:*) for API communication and Read, Write, and Edit for potential local file modifications.
  • Sanitization: The instructions include a requirement to redact sensitive data such as tokens and private comments from output, but do not specify sanitization or escaping of task content to prevent prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 08:28 PM