fireflies

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

• Third-party content exposure detected (high risk: 0.90). This skill directly queries the Fireflies.ai GraphQL API (https://api.fireflies.ai/graphql as shown in the resource script and SKILL.md via LIST_QUERY/FULL_QUERY) to fetch user-generated meeting transcripts and summaries that the agent reads and uses to produce outputs, so untrusted third‑party content can influence behavior.