Back to skill

Security audit

MetaRun: store media

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent App Store media management helper, with expected authenticated MetaRun and Apple operations and no evidence of hidden or destructive behavior beyond user-directed asset changes.

Install only if you trust MetaRun and the npm package source. Use it with an account that has only the App Store permissions needed for media work, review every preview before apply, and prefer a pinned or vetted MetaRun CLI version in sensitive environments.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
envVars:
      - name: METARUN_TOKEN
        required: false
        description: MetaRun personal access token (Settings, MCP). Not needed after `npx metarun login`, which stores it in ~/.metarun/config.json.
    requires:
      anyBins:
        - npx

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The skill instructs use of npx metarun without pinning a specific package version, which means execution depends on whatever version npm resolves at runtime. If the package is updated maliciously, compromised upstream, or unexpectedly changed, the operator could run unreviewed code with access to local files, network, and stored credentials such as MetaRun config.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

This line again directs the operator to fetch and execute tooling through unpinned npx metarun, introducing supply-chain risk. Because this skill is designed for authenticated App Store operations, compromise of the executed package could lead to credential theft or unauthorized modification of store assets.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The instruction to run npx metarun tools <tool-name> --json without version pinning creates the same remote code execution and supply-chain exposure as other npx invocations. In this context, the command may be run on a workstation holding Apple-related credentials and configuration, raising the consequences of compromise.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

Although this occurrence is framed as discovery/help text, it still instructs users to execute an unpinned package from npm. Any such invocation can run attacker-controlled or unexpected code if the upstream package or dependency chain is compromised.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.