news-summary

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

• Third-party content exposure detected (high risk: 0.90). The skill's Workflow Step 1 ("Fetch Article Content
• Use webFetch with the provided URL" in SKILL.md) explicitly fetches arbitrary news articles from the open web and then the agent reads/analyzes that content to drive summaries and decisions, exposing it to untrusted third-party content that could carry indirect prompt injection.