Security audit
Fireflies.ai
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Fireflies.ai integration that uses Maton OAuth to access meeting data and includes cautious approval rules for writes, automation, and credentials.
Install only if you want a Maton-mediated Fireflies connection. Treat meeting transcripts and recordings as sensitive business and personal data, confirm every write or automation setup, avoid third-party trigger destinations unless you understand exactly what will be forwarded, and revoke unused connections or functions when finished.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.