Back to skill
Skillv1.0.2
ClawScan security
mcpjungle · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 8:17 AM
- Verdict
- benign
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only helper for an existing mcpjungle CLI and is internally consistent with that purpose, but the package metadata omits some practical requirements (the CLI and any registry auth) which is a packaging/clarity issue rather than an obvious security problem.
- Guidance
- This is an instruction-only helper that runs an external 'mcpjungle' CLI — it does not install anything itself. Before using: (1) ensure you have the official mcpjungle CLI installed from a trusted source; (2) confirm whether your registry requires authentication and plan how to supply credentials securely (the skill does not declare or manage creds); (3) be aware the agent will run shell commands that interact with the specified registry URL, so only point it at registries you trust; and (4) consider verifying the CLI binary (checksums/signature) if obtained from the internet. The metadata omission of the required binary is a packaging issue, not evidence of malicious intent.
Review Dimensions
- Purpose & Capability
- noteThe SKILL.md and the skill name/description align: it documents CLI commands to manage an MCPJungle registry (list/register/deregister/enable/disable/invoke/etc.). However, the registry metadata lists no required binaries while the SKILL.md explicitly says the 'mcpjungle' CLI must be installed and on PATH—this is a packaging/metadata omission that could mislead users or automated installers.
- Instruction Scope
- okAll runtime instructions are concrete CLI invocations against a specified registry URL (default http://127.0.0.1:8080). The instructions do not ask the agent to read arbitrary files, environment variables, or send data to unrelated external endpoints. They stay within the stated scope of managing an MCPJungle gateway via its CLI.
- Install Mechanism
- okThere is no install spec (instruction-only), so nothing is fetched or written by the skill itself. This minimizes risk. Note: the SKILL.md expects a separately installed 'mcpjungle' CLI — the skill does not provide or document how to obtain that binary.
- Credentials
- noteThe skill declares no environment variables or credentials. The SKILL.md likewise does not show how to handle registry authentication. If the target registry requires auth (tokens, basic auth, client certs), the skill offers no guidance and the metadata does not request any credentials—this is an omission that users should be aware of, but not necessarily malicious.
- Persistence & Privilege
- okThe skill is not always-enabled and is user-invocable. It does not request persistent privileges or attempt to modify other skills or system-wide agent settings. Autonomous invocation is allowed (platform default) but not combined with other concerning flags.