mekari-taste

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md Step 1) explicitly fetches and reads Confluence URLs as PRDs—user-generated third-party content—which the agent ingests and uses to determine screens, wireframes, and implementation actions, allowing instructions in that content to influence behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly fetches and reads a user-provided Confluence URL at runtime ("If Confluence URL → fetch and read the full page"), and that fetched content is used to drive the agent's wireframe generation and planning (i.e., directly controls prompts), so a user-supplied Confluence URL is a runtime external dependency that could influence agent instructions.