add-feature

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 and files like authentication.md, email-provider.md, styling.md) explicitly instructs the agent to fetch and follow raw GitHub/Wasp docs (public third-party URLs) and to use that fetched content as the basis for configuration decisions, which exposes the agent to untrusted public content that can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs at runtime to fetch and follow raw documentation (explicitly a raw Gist URL: https://gist.githubusercontent.com/infomiho/b35e9366e16913949e13eaba0538f553/raw/c6da98158c1a7e46b5874868f2e7c011f24d24d1/0-README.md), which would directly control the agent's instructions/behavior and is required by the styling feature—constituting a runtime external dependency that can control prompts.