fireflies-core-workflow-b

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly returns and processes "Results from Fireflies.ai API" (see SKILL.md Output and Resources linking https://docs.fireflies.com), indicating it ingests third-party, user-generated meeting transcripts from an external API that the agent would read and act on, creating potential for indirect prompt injection.