pygraphistry

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

• Third-party content exposure detected (high risk: 0.75). The skill's Fast Targeted Fetch Protocol and SKILL.md explicitly instruct the agent to fetch and read pages from the public PyGraphistry ReadTheDocs site (e.g., https://pygraphistry.readthedocs.io/ and its sitemap/TOC snapshots), so the agent ingests public third‑party web content that can influence routing and subsequent actions.