Back to skill
Skillv0.3.0
ClawScan security
Company Investment Research · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 5, 2026, 8:47 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only investment research framework and templates; its declared requirements, instructions, and files are coherent with the stated purpose and do not request unexpected access to credentials, binaries, or external install artifacts.
- Guidance
- This skill is a safe, purely instructional template for producing investment memos. Before using: (1) verify any third-party data you request (Bloomberg/FactSet/etc.)—the skill does not include those feeds; (2) do not provide secrets or paid-account credentials to the agent; (3) validate numeric outputs and assumptions (LLMs can hallucinate financials); and (4) confirm licensing/attribution if you republish templates or use them commercially.
Review Dimensions
- Purpose & Capability
- okName/description (investment research framework) match the provided SKILL.md and reference docs. No binaries, credentials, or unrelated capabilities are requested.
- Instruction Scope
- okSKILL.md and reference files are templates and checklists for analyst workflows. They do not instruct the agent to read system files, access credentials, call unknown external endpoints, or exfiltrate data.
- Install Mechanism
- okNo install spec and no code files; this is instruction-only so nothing is downloaded or written to disk.
- Credentials
- okNo required environment variables, credentials, or config paths are declared or referenced. The docs mention external data sources (Bloomberg, FactSet) only as recommended sources, which is appropriate for the purpose.
- Persistence & Privilege
- okalways is false and the skill does not request system-wide persistence or modify other skills. Normal autonomous invocation is allowed by platform defaults but presents no additional red flags here.