ClawHub
Back to skill

Security audit

Fireflies.ai

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Fireflies.ai API helper that uses Maton authentication and gives cautious controls for connections, credentials, and data-changing actions.

Before installing, confirm you are comfortable giving Maton-mediated access to Fireflies meeting content, contacts, and recordings. Use OAuth where possible, approve new Fireflies connections and any mutation explicitly, and avoid the raw API-key fallback unless the CLI cannot be used.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

Medium
Confidence
94% confidence
Finding
This is a real security-relevant flaw in the skill’s operational guidance: it says all data-modifying operations require confirmation, but then broadly states that any POST requires approval. Because Fireflies GraphQL uses POST for both read-only queries and mutations, this ambiguity can cause an agent to infer safety from HTTP method incorrectly or, worse, normalize POST handling in a way that weakens the intended mutation-vs-query control boundary.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.