fireflies

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

• Third-party content exposure detected (medium risk: 0.30). At runtime, the skill’s Fireflies GraphQL CLI reads and LLM-ingests outsider-provided free text from command-line arguments (e.g., live add --action-item as prompt, and askfred create --question / askfred continue --question as query) and sends them into Fireflies via the createLiveActionItem / createAskFredThread / continueAskFredThread GraphQL operations.