Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent Chinese social-platform content rewriting aid with an optional rule-fetching script, and I found no hidden persistence, credential access, destructive behavior, or exfiltration logic in the artifact.
Install only if you want Chinese-platform content adaptation. Treat advertising-law checks as drafting guidance, not legal advice, and avoid sending confidential unpublished material to the remote API unless you are comfortable with that service handling it.
The skill claims to perform rewriting, compliance checking, and multi-platform generation, but the described implementation appears limited to retrieving/displaying rules. This mismatch can mislead users or downstream agents into trusting outputs as compliant or fully processed when no such checks actually occur, creating compliance, safety, and integrity risks.
The skill advertises an executable shell script and API-backed behavior but does not declare any tool scope or allowed-tools restrictions. In agent environments, undeclared shell capability increases the chance of unintended or overly broad command execution, reducing least-privilege protections and making later prompt- or content-driven misuse more dangerous.
The manifest description lists triggers such as "content remix," "platform adaptation," and "内容分发" without clear scope boundaries or exclusion conditions. These phrases are broad enough to overlap with generic content-editing or distribution requests, which can cause unintended invocation of this skill.
The file repeatedly defines the skill as a Chinese content remix specialist for Chinese platforms and states "You are a Chinese content remix specialist" without offering any language or locale choice. This is a natural-language locale constraint that appears forced rather than explicitly optional or justified as user-selected behavior.
The user-facing output strings on these lines are hard-coded in Chinese (for example, 标题, 正文, 标签, 语气) with no option to select another language or locale. This creates a natural-language policy issue because the skill imposes a specific language on all users without opt-in or documented regional justification.
No suspicious patterns detected.
