altmetrics-guide

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

• Third-party content exposure detected (high risk: 0.70). This skill's SKILL.md explicitly instructs querying the Altmetric.com API (see "Querying the Altmetric.com API" with requests.get to https://api.altmetric.com/v1/...), which fetches public, user-generated mentions (social media, blogs, news) that the agent is expected to read and use to interpret impact and inform decisions, exposing it to untrusted third‑party content that could contain indirect prompt-like instructions.