write-aida-article-create

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches a prompt from a public web URL at runtime (curl ... https://jeffbailey.us/prompts/aida-article-create/raw.html), which is outsider-authored free text that is read into the LLM context after caching and loading.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly performs a runtime curl to fetch and cache the prompt from https://jeffbailey.us/prompts/aida-article-create/raw.html (pipelines it through pandoc) and then uses that fetched content as the template/instructions the agent follows, so the external URL directly controls prompts at runtime.