Back to skill
Skillv1.0.0
ClawScan security
Psychology of Money Advisor · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 20, 2026, 1:37 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions and requirements are internally consistent with its stated role as a psychology-first financial advisor and it does not request unrelated credentials, installs, or system access.
- Guidance
- This skill is coherent and does not request credentials or install software. Before enabling: verify your platform actually provides the referenced 'Visualizer tool' (and confirm how it renders visuals and whether it sends data externally), and be comfortable with the skill being triggered for many finance-related user prompts (it is designed to run whenever users express financial worry or ask 'what should I do with my money'). Also verify the agent respects the skill's stated prohibitions (no tax/legal/accounting/product recommendations) in practice.
Review Dimensions
- Purpose & Capability
- okThe name/description (a counseling-style financial advisor based on The Psychology of Money) matches the SKILL.md instructions: it listens, applies behavioral frameworks, avoids legal/tax/accounting/product recommendations, and produces simple visuals. There are no unrelated credential or binary requirements. One minor note: the SKILL.md assumes a 'Visualizer tool' is available but the skill does not declare that dependency explicitly.
- Instruction Scope
- okRuntime instructions stay within the stated scope—ask/open questions, apply 14 behavioral concepts, avoid calculations/accounting/legal/tax/product recommendations, and produce quick visuals. The instructions do not ask the agent to read files, environment variables, system config, or send data to external endpoints beyond the implied Visualizer tool.
- Install Mechanism
- okInstruction-only skill with no install spec and no code files; therefore nothing is downloaded or written to disk. This is the lowest-risk install footprint.
- Credentials
- okThe skill declares no environment variables, credentials, or config paths and its behavior does not require secrets. No disproportionate access is requested.
- Persistence & Privilege
- okalways:false and the default ability for the agent to invoke the skill autonomously are appropriate for a conversational advisor. Be aware the triggering rules (use this whenever the user discusses money-related feelings or questions) mean the skill may be invoked frequently for any finance-related conversation, but this is a functional (not security) consideration.