Back to skill
Skillv1.0.0
ClawScan security
Michael Burry Investing Skill · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 15, 2026, 2:01 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only persona/heuristics pack that matches its stated purpose (emulating Michael Burry's investment voice); it requests no credentials, performs no installs, and contains no code, so its footprint is proportionate to its description.
- Guidance
- This skill is internally coherent and low-risk from a system/security perspective because it is instruction-only and asks for no credentials or installs. Practical cautions: (1) It emulates a public figure and provides investment recommendations — do not treat outputs as professional financial advice; verify any trade ideas independently or consult a licensed adviser. (2) The skill may assert factual claims (holdings, notional sizes, dates) that could be outdated or inaccurate; check primary sources (the Substack, filings, news) before acting on them. (3) If you plan to have the agent act on trades or integrate with brokerage APIs, require minimal, purpose-limited credentials and explicit human approval flows. Finally, if provenance matters to you, verify the author/homepage (meta.json points to a GitHub repo) before installing.
Review Dimensions
- Purpose & Capability
- okName/description, metadata, and SKILL.md consistently describe a Michael Burry–style investing persona and decision framework. There are no unexpected environment variables, binaries, installs, or config paths required that would be unrelated to that goal.
- Instruction Scope
- noteThe SKILL.md is an extensive instruction set for voice, reasoning rules, examples and historical references — all internal to the skill. It does not instruct the agent to read local files, access system environment variables, or call external endpoints beyond citing public sources. Note: because the skill is explicitly designed to give investment reasoning and recommendations in a named person's voice, users should be aware of financial/advice and impersonation risks (legal/ethical), and the agent may confidently state claims that are outdated or speculative if prompts aren't constrained.
- Install Mechanism
- okNo install spec and no code files to write to disk; instruction-only skills are low risk from an installation/execution standpoint.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths and the runtime instructions do not reference secrets — this is proportional for a persona/heuristics skill.
- Persistence & Privilege
- okThe skill is not flagged always:true and uses normal agent invocation. It does not request persistent system-wide privileges or modify other skills' configs.