v1.1.0

🇨🇳 中国市场政策查询Skill

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 6:37 AM.

Analysis

This is an instruction-only policy lookup skill with no code, install script, or declared credential use, though users should not over-rely on its “trusted/calibration” claims.

GuidanceThis skill appears safe to install as an instruction-only reference aid, but do not treat its policy answers as authoritative legal or trade advice, and be cautious if any runtime unexpectedly requests credentials.

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Human-Agent Trust Exploitation

SeverityLowConfidenceMediumStatusNote

_meta.json

"trustedMode": true

The metadata labels the skill as using a trusted mode, which is a trust assertion not backed by visible source data or code in the artifacts.

User impactUsers may place more confidence in the skill's policy answers than the artifacts justify.

RecommendationTreat outputs as informational and verify important tariff, customs, or legal conclusions against official Chinese government or customs sources.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityLowConfidenceMediumStatusNote

capability signals

requires-sensitive-credentials

This signal conflicts with the provided requirements and SKILL.md statements that no API key or environment variables are required, but the artifacts do not show actual credential collection or use.

User impactIf an installer or runtime unexpectedly asks for secrets, that would not match the visible skill documentation.

RecommendationDo not provide credentials unless the platform clearly explains why they are needed and the request matches the documented purpose.