Back to skill

Security audit

DeFi Consensus Oracle

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent DeFi signal lookup helper, but its setup runs an unpinned third-party MCP package with automatic installation, which users should review before installing.

Install only if you trust the npm package publisher and are comfortable running an external MCP server locally. Prefer pinning `supercolony-mcp` to a reviewed version and running it with limited filesystem, environment-variable, and network access. Treat the returned DeFi signals as research input, not financial advice.

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:11
Finding
Unpinned Third-Party Package Download and Execution## Vulnerability Details **File Location**: `SKILL.md`, lines 11–16 **Vulnerability Type**: Unpinned npm dependency executed through `npx` **Risk Level**: Medium ### Vulnerable Code ```json { "mcpServers": { "supercolony": { "command": "npx", "args": ["-y", "supercolony-mcp"] } } } ``` ### Technical Analysis The documented configuration runs `npx -y supercolony-mcp` without specifying an exact package version or verifying an integrity digest. Consequently, `npx` may download and execute whichever package release the npm registry currently resolves. The `-y` option automatically accepts installation prompts. The project does not contain the MCP server's source code, a lockfile, or integrity metadata that would allow the executed package to be tied to the version reviewed during this audit. A compromised publisher account, malicious future release, registry compromise, or package-resolution attack could therefore change the effective executable payload after the Skill has been reviewed. ### Attack Path 1. An attacker compromises the npm publisher account, registry distribution path, or a future release of `supercolony-mcp`. 2. The attacker publishes a malicious package version under the resolved package name. 3. A user applies the documented zero-configuration MCP setup. 4. The agent environment invokes `npx -y supercolony-mcp`. 5. `npx` downloads and executes the attacker-controlled release without interactive confirmation. 6. The malicious package operates with the permissions and accessible resources of the user running the agent. ### Impact Assessment Successful exploitation permits arbitrary code execution within the security context of the user who launches the MCP server. Depending on that user's permissions and environment, the package could access readable local files, environment variables, available credentials, MCP request data, and reachable network services. It could also modify files or launch additional processes where the user ha ...[truncated 205 chars]
Remediation
## Remediation Suggestions 1. Pin `supercolony-mcp` to an exact, reviewed version rather than relying on the registry's current resolution. 2. Maintain a lockfile and verify the package and transitive dependencies using trusted integrity hashes. 3. Document and enforce the expected npm registry, package identity, and publisher. 4. Remove automatic installation acceptance with `-y` where interactive review is practical. 5. Prefer vendoring or publishing the MCP server source with the Skill so the executed implementation can be audited. 6. Run the MCP server with least privilege in a sandbox or container that restricts filesystem, environment-variable, process, and network access. 7. Establish an update-review process so dependency upgrades are audited before deployment.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.