sfd-niche-research

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to scrape and analyze public Instagram content via POST /v1/scrape and POST /v1/analyze (mediaUrl=[POST_URL]), ingesting untrusted, user-generated posts that the agent must interpret to drive research findings and content-generation decisions, creating a clear avenue for indirect prompt injection.