parallel-findall

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md instructs running parallel-cli findall which returns matched entities and source URLs from public websites and explicitly requires the agent to "spot-check the kept entries against the source URL" and "cite each entity with its source URL," meaning the agent ingests and acts on untrusted, user-generated/public web content (third-party webpages) as part of its workflow.