Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward PRD document generator with no executable code, hidden data access, or persistence beyond normal skill installation.
Install this if you want a Chinese-oriented structured PRD generator. Be aware it may activate on broad requirements-document requests, so review generated PRDs for scope and language fit before relying on them.
The trigger phrases are broad enough to match many ordinary product or documentation requests, which can cause the skill to activate outside its intended scope. In an agent environment, over-broad activation increases the chance of unintended prompt injection exposure, user confusion, or the wrong automation being applied to unrelated tasks.
The skill’s activation examples include very broad phrases such as generic requests to 'write a PRD' or 'generate a requirements document', which can cause the orchestrator to invoke this skill in situations where the user did not specifically want this structured PRD workflow. While this is not an exploit primitive by itself, over-broad triggering can lead to misrouting, unnecessary collection of business details, and generation of overly prescriptive artifacts in the wrong context.
The natural-language description is written entirely in Chinese and presents the skill as a Chinese PRD generator, with no indication that users can choose another language or locale. This can violate language/locale policy when a skill appears to prescribe a specific language experience without explicit opt-in or justification.
No suspicious patterns detected.
