breach-data-analysis

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

• Third-party content exposure detected (low risk: 0.10). The skill “Breach Data Analysis” workflow (as described in SKILL.md) only references using first-party breach-check services like Have I Been Pwned and paid searchable databases, but no required runtime step is specified that would ingest outsider-authored free text without the agent first selecting specific items to fetch/check.