context7-auto-research

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly states the skill "automatically fetch[es] latest library/framework documentation for Claude Code via Context7 API," so the agent ingests external/public third-party documentation from the open web (via the Context7 API) as part of its workflow, which can materially influence decisions and enable indirect prompt injection.