daily-social-agent

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly requires the agent to "scan ... web trends" / perform web search and pull from content archives (open/public sources) as part of its mandatory workflow, meaning untrusted public content is read and used to decide and generate social-post drafts that materially influence the agent's actions.