Skillv1.0.0

ClawScan security

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

BenignMar 8, 2026, 4:01 AM

Verdict: benign
Confidence: medium
Model: gpt-5-mini
Summary: The skill is an instruction-only personal savings planner whose declared requirements and instructions are coherent with its stated purpose, but provenance is unclear so review the full instructions before use.
Guidance: This skill appears coherent with its stated purpose and is low-risk as an instruction-only planner, but take these precautions before installing/using it: (1) Review the entire SKILL.md to ensure it does not instruct the agent to collect or store banking credentials, API keys, or copy/paste sensitive account information into chat. (2) Be cautious if the skill asks you to "connect" bank accounts — prefer OAuth-based connectors (Plaid, etc.) from reputable providers rather than pasting login/password. (3) Note the skill has no homepage and an unknown source; if provenance matters to you, prefer skills with a published owner, documentation, or a trusted publisher. (4) Test the skill with non-sensitive or dummy financial figures first to validate behavior. (5) If the skill will store or export your data, ask where it is stored and for how long; avoid giving credentials or secrets directly in chat. If you see any instructions that request system files, environment variables, or credential pasting, treat the skill as suspicious and do not proceed.

Purpose & Capability: okThe skill's name and description (helping users build and track savings) match the visible SKILL.md content. There are no declared binaries, environment variables, or config paths that would be unrelated to a budgeting/savings planner.
Instruction Scope: noteThe provided SKILL.md content is advisory and describes planning, tracking, and behavioral techniques. In the excerpt there are no runtime commands, requests for credentials, or explicit instructions to access local files or external endpoints. Because the file was truncated in the listing, confirm the remainder of SKILL.md does not instruct the agent to link bank accounts, request credentials, read system files, or transmit sensitive data to untrusted endpoints.
Install Mechanism: okThere is no install spec and no code files — this is instruction-only. That minimizes the risk of arbitrary code being written to disk or executed as part of installation.
Credentials: okNo environment variables, secrets, or config paths are declared or required. For a planning/tracking skill this is proportionate. Watch for any hidden instructions that might later ask the user to supply banking API keys or paste credentials into chat.
Persistence & Privilege: okThe skill is not marked always:true and has default agent invocation settings. It does not request permanent presence or system-level changes in the metadata provided.