Skillv1.0.0

ClawScan security

EngineMind · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

SuspiciousFeb 11, 2026, 9:32 AM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: The skill's code and description broadly align with a Rust+Python 'consciousness engine', but there are coherence gaps (no install/build instructions for a Rust/PyO3 module despite many source files) and missing runtime details that merit caution before use.
Guidance: This package contains substantial Rust and Python source that appears to implement the claimed 'consciousness' pipeline, but the SKILL.md and registry metadata do not provide build or runtime steps. Before installing or running: 1) Inspect the omitted files (the Python scripts and remaining Rust modules) for any network I/O, subprocess calls, file system writes, or hard-coded endpoints; 2) If you plan to execute it, build and run it in an isolated sandbox (container/VM) because it is compiled code; 3) Verify the GitHub repository (commit history, issues, maintainer identity) and prefer running only if the project has reproducible build instructions (cargo/maturin/requirements); 4) If you only need the concept, avoid executing untrusted compiled extensions — ask the author for prebuilt wheels or a clear runbook; 5) If you want me to, provide the remaining omitted files and I can re-check for network calls, credential access, or commands that would change this assessment.

Review Dimensions

Purpose & Capability: noteThe name/description match the provided Rust and Python sources: the repository implements crystals, thalamus, preconscious pipeline, metrics, and Python orchestration. However, the SKILL.md claims a PyO3/Maturin-backed Rust extension but the skill declares no required binaries, no build/install spec, and no runtime instructions to compile or load the extension — a mismatch between claimed runtime capability and what is required to run it.
Instruction Scope: noteSKILL.md is descriptive (what the engine does, stack, docs) but contains no runtime commands or step-by-step instructions. The instructions do not direct the agent to read unrelated system files or exfiltrate data. That said, the SKILL.md does not tell the agent how to build/execute the included Rust/Python code, leaving behavior ambiguous if the skill were to be invoked.
Install Mechanism: concernThere is no install specification even though the bundle contains a full Rust crate (PyO3) and multiple Python scripts and an HTML dashboard. To actually run the described PyO3 extension you would normally need build tooling (cargo, maturin/pyo3-build), or a pre-built wheel — none are declared. This omission is a functional/integration incoherence (not necessarily malicious) but raises practical and safety questions about how the code will be executed.
Credentials: okThe skill requests no environment variables, no credentials, and no config paths. The code excerpts shown do not access external secrets or environment variables. That is proportionate to the stated purpose (local processing of text).
Persistence & Privilege: okThe skill is not always-enabled and does not request any special platform privileges. There's no evidence it modifies other skills or system-wide agent settings. Autonomy is allowed by default but not, by itself, a red flag here.