blueprint-scratchpad

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Process (SKILL.md, step 1) explicitly fetches a Linear project and its tickets and "scan[s] descriptions and comments for links (Notion, Figma, Slack). Fetch each using MCP tools," meaning it ingests user-generated third-party content which the agent reads and uses to form recommendations and next actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). This skill fetches user-provided Linear project links (e.g., https://linear.app/...) and linked Notion/Figma/Slack URLs at runtime and injects that fetched content into the agent's context to drive its questions and outputs, so those external URLs can directly control agent prompts.