Skills
skills/cold-iq/coldiq-marketplace-skills/fireflies-usage/Gen Agent Trust Hub

fireflies-usage

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill uses official integration methods for Fireflies.ai.
  • [EXTERNAL_DOWNLOADS]: The skill uses the fireflies-mcp-server npm package as part of the MCP setup.
  • [COMMAND_EXECUTION]: The MCP configuration executes npx to initialize the Fireflies server.
  • [PROMPT_INJECTION]: The skill processes meeting transcripts from Fireflies.ai, which represents a surface for indirect prompt injection. 1. Ingestion points: fireflies_get_summary and fireflies_get_transcript tools. 2. Boundary markers: No delimiters or warnings are specified for the processed transcript content. 3. Capability inventory: The skill is used to ground campaign work and extract action items. 4. Sanitization: No explicit sanitization of transcript data is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:02 PM
Security Audit — agent-trust-hub — fireflies-usage