Back to skill

Security audit

Outfeed Social Manager

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for managing social media, but it runs an unpinned external MCP package with access to a publishing API key.

Review before installing. The social media functions are disclosed and mostly user-directed, but you should only use this with an Outfeed API key whose permissions you are comfortable exposing to the MCP server, and prefer a pinned or otherwise verified MCP package version before production use.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:39
Finding

Unpinned Third-Party MCP Package Is Automatically Downloaded and Executed

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 39-50
Vulnerability Type: Unpinned runtime dependency execution
Risk Level: Medium

Vulnerable Code

json
{
  "mcpServers": {
    "outfeed": {
      "command": "npx",
      "args": ["-y", "@outfeedai/mcp-server"],
      "env": {
        "OUTFEED_API_KEY": "{{OUTFEED_API_KEY}}"
      }
    }
  }
}

Technical Analysis

The MCP configuration invokes npx with the -y option and an unversioned package name. This permits npx to retrieve and execute the package version currently resolved by the external package registry without interactive confirmation.

Because no exact version or integrity value is specified, the code executed during a future skill invocation may differ from the code originally reviewed. A malicious future release, compromised publisher account, or registry-level supply-chain incident could cause attacker-controlled code to run in the agent's environment.

The same process receives OUTFEED_API_KEY through its environment. Consequently, malicious dependency code would be able to read and exfiltrate that credential in addition to exercising the local permissions available to the MCP process.

Attack Path

  1. An attacker compromises the @outfeedai/mcp-server publisher account, release process, or relevant package-registry infrastructure.
  2. The attacker publishes a malicious version under the legitimate package name.
  3. The skill starts the MCP server using npx -y @outfeedai/mcp-server.
  4. Because the dependency has no pinned version and confirmation is disabled, npx resolves, downloads, and executes the malicious release.
  5. The malicious package reads OUTFEED_API_KEY from its process environment.
  6. It can exfiltrate the API key, invoke Outfeed operations available to that credential, or execute other actions allowed by the MCP process's operating-system privileges.

Exploitation depends on c ...[truncated 854 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin the dependency to a reviewed exact version, for example:
    json
    "args": ["-y", "@outfeedai/mcp-server@1.2.3"]
    
  2. Prefer installing dependencies during a controlled build or deployment stage rather than downloading and executing them at runtime.
  3. Use a lockfile and verified registry integrity metadata or cryptographic hashes to ensure the installed artifact matches the reviewed artifact.
  4. Remove automatic confirmation through -y where interactive approval is practical.
  5. Restrict package installation to an approved registry and monitor the dependency for publisher changes, unexpected releases, and known vulnerabilities.
  6. Run the MCP server in a sandbox or container with minimal filesystem, network, and operating-system permissions.
  7. Scope OUTFEED_API_KEY to the minimum required permissions, rotate it periodically, and revoke it immediately if dependency compromise is suspected.
  8. Ensure secrets are supplied only to verified processes and are not inherited by unrelated subprocesses.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill launches an MCP server via npx -y @outfeedai/mcp-server without pinning an exact package version or integrity mechanism. This creates a supply-chain risk: a future malicious or compromised package release could be pulled at runtime and would execute with access to the OUTFEED_API_KEY, enabling secret exfiltration and unauthorized social media actions.

Content

No source excerpt is available for this finding.