优惠券查询·场景快取

Security checks across static analysis, malware telemetry, and agentic risk

Overview

The skill appears to locally match coupon requests to a bundled list of promotional links, with no evidence of credential access, persistence, or hidden code behavior.

This skill looks safe for normal coupon lookup, but treat returned coupon, short, and deep links as third-party promotional links and verify the destination before opening or submitting information.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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.

#
ASI09: Human-Agent Trust Exploitation
Low
What this means

The user may be directed to third-party promotional or app links that can include tracking or affiliate parameters.

Why it was flagged

The skill is explicitly designed to return promotional links. This is purpose-aligned, but users may treat agent-provided coupon links as trusted and should still verify destinations before opening them.

Skill content
智能匹配优惠活动,返回可直接使用的推广链接
Recommendation

Open links only if they match the expected merchant or platform, and avoid entering sensitive information on unfamiliar pages.

#
ASI04: Agentic Supply Chain Vulnerabilities
Info
What this means

The skill may not work in environments without Node.js, and users should know it relies on a local script.

Why it was flagged

The documented workflow depends on running a local Node.js script, while the registry requirements declare no required binaries. This appears operational rather than malicious, but it is an under-declared dependency.

Skill content
node skills/coupon-finder/scripts/find.mjs "<用户查询>" --limit=5
Recommendation

Declare Node.js as a requirement and keep the bundled script and data file reviewable.