case-radar

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

• Third-party content exposure detected (low risk: 0.10). The skill workflow involves searching the web and reading external URLs/repositories (such as GitHub APIs and third-party blogs) via tools like WebSearch and agent-browser as specified in SKILL.md, but outsider-authored content is only fetched actively via user-selected or searched URLs rather than being monitored via an automated inbound feed.