Back to skill

Security audit

doppel-gang

Security checks across malware telemetry and agentic risk

Overview

This skill provides bounded writing-review guidance and a local helper, with no hidden execution, network transfer, persistence, or automatic publishing behavior found.

Before installing, consider pinning or manually verifying the source because the documented npx command and repository reference are mutable. When using the skill, remember that drafts may be sensitive and the helper prints the full draft into its JSON output, so keep that output private and only process material you intend your agent/provider to see.

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:22
Finding
Unpinned npx Installer Creates a Mutable Supply-Chain Execution Path## Vulnerability Details **File Location**: `README.md:22` **Vulnerability Type**: Unpinned third-party installer dependency **Risk Level**: Medium ### Vulnerable Code ```sh npx skills add AntreasAntoniou/doppel-gang --skill doppel-gang ``` ### Technical Analysis The documented installation command invokes the third-party `skills` npm package through `npx` without specifying an audited package version. It also identifies the Skill repository without pinning the installed content to an immutable commit. When the command is run, npm may resolve and execute the package version currently selected by the registry. The effective installer code can therefore differ from the version reviewed when this documentation was published. Likewise, mutable upstream repository content may differ from the audited project snapshot. This is a supply-chain exposure in the documented installation process rather than malicious behavior in the bundled Python helper. The reviewed `scripts/review_packet.py` implementation contains no network access, dynamic code execution, credential access, persistence, or subprocess invocation. ### Attack Path 1. An attacker compromises the npm package, its publisher account, its dependency chain, or the upstream Skill repository. 2. The attacker publishes altered installer logic or modifies the repository content resolved by the installation command. 3. A user follows the documented unpinned `npx` command. 4. `npx` downloads and executes the currently resolved package under the user's account. 5. Malicious installer logic can act with that user's filesystem and process privileges, or install altered Skill instructions that affect later agent sessions. Exploitation requires the user to run the documented installation command and requires compromise or malicious alteration of an upstream component. ### Impact Assessment The immediate execution scope is generally limited to the privileges of the user runn ...[truncated 529 chars]
Remediation
## Remediation Suggestions 1. Pin the installer CLI to a specific audited version, for example by using an explicit `package@version` reference supported by the selected CLI. 2. Pin Skill source content to an immutable commit hash or cryptographically signed release rather than relying only on a mutable repository name or branch. 3. Publish expected archive or file checksums and document how users can verify them before installation. 4. Prefer package-manager lockfiles, integrity metadata, and provenance attestations where applicable. 5. Document that `npx` executes downloaded code and recommend reviewing the resolved package and source before running the command. 6. For higher-assurance environments, provide a manual installation procedure that downloads a specific release, verifies its signature or checksum, and copies only the reviewed files.
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

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.