Security Intelligent Marketing
PassAudited by ClawScan on May 11, 2026.
Overview
This is an instruction-only financial marketing helper with no code or permissions, but users should protect customer data and review generated financial promotions before use.
This appears safe to install as an instruction-only assistant. Before using it with real banking or securities customers, anonymize sensitive data when possible and require compliance review of any generated financial marketing content.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Customer financial details or personal attributes could appear in prompts, transcripts, or generated outputs if raw records are used.
The skill is designed to analyze customer financial and demographic attributes. This is purpose-aligned, but real customer records would become part of the agent interaction context if provided.
assets = customer.get("total_assets", 0) ... risk = customer.get("risk_preference", "稳健型") ... age = customer.get("age", 30) ... transaction_frequencyUse anonymized or approved datasets where possible, provide only the minimum customer fields needed, and avoid enabling any platform memory or retention features for sensitive customer data.
If used directly, generated ads, posters, or SMS copy could overstate benefits or omit required risk warnings.
The marketing templates include persuasive financial-product language about returns, urgency, and scarcity. This matches the skill purpose, but financial promotions can mislead if claims are unverified or disclosures are missing.
年化收益最高{收益率} ... 立即抢购 ... 名额有限，先到先得Treat generated content as a draft only; verify rates and claims, add required financial-risk disclosures and opt-out language, and obtain compliance/legal review before sending or publishing.