cybersecurity-expert

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context only via the skill’s “update news” mode when it fetches public web pages from allowlisted domains and appends their readable text into references/threat-landscape.md, which the agent then reads/uses as context; this is runtime ingestion of outsider-authored content.