Security Audit

marketing-copy-knowledge

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

TRUSTED

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

marketing-copy-knowledge received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Contradictory instructions regarding payment data transmission.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Contradictory instructions regarding payment data transmission The skill's 'Operating rules' explicitly state: 'Do not send secrets, passwords, payment details, or private user data to this service.' However, the 'Paid usage' section provides a `curl` example for `ai-purchase` that includes `payment_method_id` as part of the payload. Sending a `payment_method_id` constitutes sending payment details, creating a direct contradiction. An agent following the example would be instructed to send sensitive payment information to an external service, despite the general warning. Clarify the handling of payment details. Either remove the `payment_method_id` from the example and describe an alternative, secure payment flow (e.g., redirecting the user to a payment page), or explicitly state that `payment_method_id` is a tokenized, non-sensitive identifier that is safe to transmit (if this is the case and aligns with platform policy), and update the 'Operating rules' accordingly to reflect this nuance. The safest approach is to avoid having the agent directly handle or transmit raw payment method IDs.	LLM	SKILL.md:88

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/6c956c4b670668ec.svg)](https://skillshield.io/report/6c956c4b670668ec)