Mumara

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.4

Overview

The skill appears to be a legitimate Mumara integration, but it exposes broader administrative API access than its narrow description makes clear.

Install only if you intend to give the agent broad authenticated access to Mumara. Review any requested write, delete, campaign, or raw API action before approving it, and prefer a least-privilege Mumara account where possible.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Description-Behavior Mismatch

Medium

• Confidence: 89% confidence
• Finding: The manifest says the skill is for managing users and organizations, but the body documents much broader Mumara administration and direct proxy access to arbitrary API endpoints. This scope mismatch can mislead routing and approval decisions, causing the agent or user to invoke a much more powerful skill than expected.

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The invocation description is very broad ('interact with Mumara data'), which may cause the skill to be selected for many generic prompts involving Mumara. Because the skill exposes broad administrative and arbitrary API capabilities, overbroad triggering increases the chance of unintended sensitive actions or data access.

VirusTotal

64/64 vendors flagged this skill as clean.