Back to skill
Skillv2.0.0
ClawScan security
吴军投资智慧 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 20, 2026, 3:10 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's declared purpose (investment analysis using 吴军 principles) matches its instructions and resources; it requires no credentials, binaries, or installs and does not attempt unrelated access.
- Guidance
- This skill is internally consistent and requires no special permissions, but remember: (1) it provides generic investment analysis and is not a substitute for professional financial advice; verify any factual data (financials, market share, patents) against authoritative sources before acting; (2) do not paste sensitive or confidential company documents into the skill—only provide the non-sensitive fields the templates request; (3) confirm the authorship/trustworthiness of the packaged content if you need provenance (source/homepage is missing).
Review Dimensions
- Purpose & Capability
- okName/description and included SKILL.md, templates, and references consistently implement an investment-analysis assistant based on 吴军's ideas. There are no requested env vars, binaries, or unrelated dependencies that would be inconsistent with the stated purpose.
- Instruction Scope
- okRuntime instructions are self-contained: they ask for company/industry input and prescribe structured analyses (technology, data assets, market position, and recommendations). They do not instruct reading system files, environment variables, or contacting external endpoints beyond producing analysis text.
- Install Mechanism
- okNo install spec and no code files; this is an instruction-only skill so nothing is written to disk or fetched during install.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The data it requests (company_name, industry, tech/data/market info) is proportional to an investment analysis task.
- Persistence & Privilege
- okalways is false (no forced inclusion). disable-model-invocation is false (normal autonomous invocation allowed), which is expected for a user-invocable analysis skill and not combined with any broad credential access.