Back to skill
Skillv1.0.0
ClawScan security
Opportunity Assessment · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 4, 2026, 12:03 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only sales opportunity / risk-assessment skill whose instructions, required resources, and outputs are coherent with its stated purpose and do not request unrelated credentials or system access.
- Guidance
- This skill appears coherent and low-risk: it only contains instructions and reference docs for conducting opportunity/risk assessments. Before installing, confirm the skill source (unknown owner) if you require provenance. Be mindful of what you send the skill: do not share highly sensitive customer data or credentials in prompts or attachments. Because the skill is an instruction-only template, review outputs for correctness and adapt any company-specific legal/contract/payment rules before acting on its advice. If you need auditability, ask the publisher for provenance or a changelog.
Review Dimensions
- Purpose & Capability
- okName and description (商机判断与风险评估) match the SKILL.md content: it defines question templates, risk dimensions, output formats, and uses two local reference docs. It does not request unrelated binaries, env vars, or credentials.
- Instruction Scope
- okRuntime instructions are limited to asking the user contextual questions and producing textual risk assessments and checklists. They reference only the included local reference files. There are no steps to read arbitrary system files, exfiltrate data, or contact external endpoints.
- Install Mechanism
- okNo install spec or code files beyond plain text docs — nothing is downloaded or written to disk by an installer. This minimizes install-time risk.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. That aligns with its purely conversational/assessment role.
- Persistence & Privilege
- okalways is false and the skill does not request persistent privileges or modifications to other skills or agent configs. Autonomous invocation is allowed (platform default) but not combined with other red flags here.