article-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to "Fetch the webpage content using WebFetch" for user-provided URLs (blogs, Substack, Medium, newsletters, web pages), so it ingests arbitrary public, user-generated web content and uses that content to generate analysis and save reports, which could allow indirect prompt injection from those sources.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches arbitrary user‑supplied webpage URLs at runtime via WebFetch (i.e., any user-provided https://... URL) and injects that fetched article content into the model context to drive the analysis, so attacker‑controlled pages could directly control prompts or influence execution.