Back to skill
Skillv1.0.0

ClawScan security

Basal Ganglia Memory 0.1.1 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignFeb 28, 2026, 12:54 PM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
This is an under-development, instruction-only placeholder that declares no binaries, no installs, and no credential or file access — it appears coherent with its stated purpose but currently provides no functioning behavior.
Guidance
This skill is a non-functional, 'coming soon' entry: it contains only descriptive text and no code, installs, or credential requests, so it doesn't pose an immediate risk but also doesn't provide functionality yet. Before installing or enabling future updates: (1) prefer skills that include source/homepage and a reputable owner; (2) review any new install steps or required environment variables (especially STORAGE, DB, or CLOUD credentials); and (3) re-check runtime instructions for file access, network endpoints, or background persistence before granting model autonomy.

Review Dimensions

Purpose & Capability
okThe name/description (habit/procedural memory) matches the SKILL.md content. The skill makes no demands (no env vars, no binaries, no install) which is proportionate for a descriptive, in-development skill. It does promise features that would eventually need storage/learning infrastructure, but nothing here claims or requests those resources now.
Instruction Scope
okSKILL.md is purely descriptive and contains no runtime commands, file paths, or instructions to read environment variables or transmit data. Because it contains no actionable runtime instructions, it cannot perform out-of-scope actions in its current form. Note: it is vague and marked 'Under Development', so future versions could add broader behavior.
Install Mechanism
okThere is no install spec and no code files; nothing will be written to disk or downloaded by this package as presented.
Credentials
okThe skill declares no required environment variables, credentials, or config paths. That is proportionate to the current non-functional, documentation-like state. If future releases implement habit-tracking, expect the addition of persistent storage or API keys — those should be reviewed when introduced.
Persistence & Privilege
okalways is false and there are no install hooks or self-modifying instructions. Model invocation is allowed by default (normal); combined with the current lack of functionality, there is no privilege escalation risk at present. Future changes that add persistent agents, background tasks, or storage would warrant re-review.