og-image-generation

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

• Third-party content exposure detected (low risk: 0.10). The required workflow involves fetching and reading documentation from a remote URL (fullstackrecipes.com) which exposes the agent to outsider-authored web content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches a remote markdown recipe via curl from an external domain, constituting a weak operational dependency.