tasks-build
Warn
Audited by Snyk on Mar 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly directs the agent to fetch and read a user-supplied Notion page URL ("Fetch the task details" step), meaning the agent ingests arbitrary user-generated Notion content that can influence its implementation and actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill fetches the user-provided Notion task URL (e.g., a Notion page like https://www.notion.so/...) at runtime and uses the fetched page content (acceptance criteria/specs) to directly control the agent's instructions and work, and this Notion content is a required dependency.
Audit Metadata