Back to skill

Security audit

davinci-mode

Security checks for vulnerabilities and agentic risk

Overview

This is a small instruction-only skill for comparing design options, with one install-time supply-chain caution from an unpinned npx command.

Before installing, prefer a pinned or manually inspected installation path instead of blindly running the unpinned npx command. Once installed, the skill is only guidance for decision framing and does not ask for credentials, background access, or authority to make changes on its own.

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
README.md:12
Finding
Unpinned Third-Party Package Execution During Installation<![CDATA[ ## Vulnerability Details **File Location**: `README.md:12` **Vulnerability Type**: Unpinned external package execution **Risk Level**: Medium ### Vulnerable Code ```bash npx skills add AntreasAntoniou/davinci-mode ``` ### Technical Analysis The documented installation command invokes `skills` through `npx` without specifying a reviewed package version or integrity hash. If the package is not already available locally, `npx` may resolve, download, and execute the currently published version from the configured npm registry. Consequently, the code executed during installation is not fully represented by this repository and can change after this skill has been reviewed. Compromise of the package publisher, npm account, registry resolution, or a subsequently published package version could cause arbitrary package code to run when a user follows the installation instructions. The referenced skill source, `AntreasAntoniou/davinci-mode`, is also not tied to an immutable commit in the documented command. However, the confirmed executable supply-chain exposure is the unpinned `npx` package. ### Attack Path 1. An attacker compromises the publisher account or release process for the npm package resolved as `skills`, or otherwise causes a malicious version to be selected through the user's registry configuration. 2. The attacker publishes a version containing malicious CLI or lifecycle behavior. 3. A user follows the command in `README.md:12`. 4. `npx` resolves and downloads the unpinned package version. 5. The downloaded package executes with the permissions and environment of the invoking user. 6. The malicious package can access resources available to that user, subject to operating-system controls and the execution environment. ### Impact Assessment Successful exploitation could permit arbitrary code execution with the privileges of the user running the installation command. Depending on that user's environment, this may expose local files, environ ...[truncated 437 chars]
Remediation
<![CDATA[ ## Remediation Suggestions 1. Pin the installer package to a specific reviewed version, for example: ```bash npx --yes skills@<reviewed-version> add AntreasAntoniou/davinci-mode ``` 2. Where the tooling supports it, pin the skill source to an immutable commit or verified release rather than a mutable repository default branch. 3. Document the expected npm package name, publisher, version, and checksum or provenance information so users can verify what will execute. 4. Prefer an installation workflow that downloads and inspects the package before execution, or make the documented manual installation method the primary recommendation. 5. Use npm provenance, signed releases, lockfiles, and integrity verification where applicable. 6. Re-review and intentionally update pinned versions rather than automatically executing the latest available release. ]]>
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
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Static analysis

No suspicious patterns detected.