fireflies-usage

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses Fireflies MCP tools (e.g., fireflies_get_transcript / fireflies_get_summary) to ingest meeting transcripts/summaries authored by third parties (meeting participants) into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill's setup instructs running "npx -y fireflies-mcp-server", which at runtime fetches and executes remote npm package code from the npm registry (i.e., a remote executable dependency), so it is a runtime external dependency that executes remote code; the GraphQL endpoint https://api.fireflies.ai/graphql is a normal data API and not flagged.