Back to skill

Security audit

Musician Manager

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent music-management helper, but it broadly covers public posting, fan messaging, analytics, and contract review without clear consent, confirmation, or sensitive-data handling limits.

Install only if you are comfortable treating this as a broad band-management assistant. Before using it, require explicit approval before any post, email, SMS, DM, phone call, calendar change, or payment follow-up, and avoid sharing unredacted contracts or fan lists unless you understand where that data will go.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises itself for essentially 'any music industry task,' which creates an overly broad activation scope and increases the chance the agent is invoked in contexts involving payments, contracts, outreach, or messaging without clear guardrails. Broad scope is dangerous because it encourages autonomous handling of high-risk actions and sensitive workflows that need explicit user confirmation and narrower task boundaries.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill describes social posting, fan email/SMS announcements, analytics, and cross-platform posting without any warning about consent, recipient privacy, platform permissions, or confirmation before outbound actions. This is risky because it could lead to accidental mass messaging, unauthorized posting, or misuse of fan data, all of which have privacy, reputational, and compliance consequences.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The contract-analysis workflow invites users to share contracts and have the skill analyze them, but it does not warn that these documents may contain sensitive legal, financial, and personal information. In this context, missing handling guidance is dangerous because users may upload confidential agreements without understanding retention, access, or the limits of AI legal review.

Content

No source excerpt is available for this finding.