sales-fireflies

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a technical assistant for the Fireflies.ai platform, providing detailed documentation on its GraphQL API, pricing tiers, and native integrations.
  • [EXTERNAL_DOWNLOADS]: The skill references official resources from the Fireflies.ai GitHub organization and official domain, as well as well-known technology partners like Salesforce, HubSpot, and n8n. These references are used solely for user documentation.
  • [PROMPT_INJECTION]: The skill utilizes a self-updating knowledge mechanism through the 'references/learnings.md' file. This creates a data ingestion surface where the agent records discovered platform tips for future sessions.
  • Ingestion points: Data is read from 'references/learnings.md' at the start of the session and written to it when new 'gotchas' or workarounds are identified.
  • Boundary markers: No explicit delimiters or boundary instructions are defined for the learning file content.
  • Capability inventory: The skill possesses file-read and file-write capabilities restricted to the local reference files.
  • Sanitization: No explicit sanitization or validation of accumulated learnings is performed before storage.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 06:01 PM