Back to skill

Security audit

MetaRun: review inbox

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent MetaRun review-management helper with explicit user approval required before public replies are posted or deleted.

Before installing, make sure you trust MetaRun and are comfortable granting it access to review workflows. Treat public review replies as sensitive: approve each final text carefully, and prefer a pinned or preinstalled MetaRun CLI if your environment requires stricter supply-chain control.

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 16)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
88% confidence
Finding

The skill instructs use of npx metarun without pinning an exact package version, which means each invocation may fetch and execute whatever code is currently published under that package name. In a skill that can access review workflows and may operate with stored credentials, a compromised or malicious upstream package could execute arbitrary code or exfiltrate tokens.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

This invocation again relies on unpinned npx metarun, creating a supply-chain execution risk because the resolved package can change over time. Since the command is used to drive external tooling for review operations, compromise of the package could lead to arbitrary command behavior, data access, or credential theft.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

Fetching tool schemas with an unpinned npx metarun still executes code from the latest published package rather than a reviewed version. Even though this looks read-only, a compromised package could perform arbitrary local actions when run.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

This duplicate occurrence on the same line represents another unpinned npx metarun reference and carries the same package-substitution and malicious-update risk. In context, the skill encourages broad tool discovery, which can increase frequency of exposure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.