pm-skills

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

• Third-party content exposure detected (high risk: 0.80). The atlassian-admin SKILL.md explicitly instructs the agent to "verificar a auto-avaliação de segurança do fornecedor em marketplace.atlassian.com" and to "revisar documentação de segurança do fornecedor" (i.e., read vendor pages on the public Atlassian Marketplace), which are untrusted third‑party webpages whose content the agent is expected to read and that can materially affect decisions about installing/configuring apps.