Security audit
Security checks for vulnerabilities and agentic risk
The skill is a work-reflection helper, but it tells the agent to automatically persist work-session details that may be sensitive without clear consent, retention, or deletion controls.
Install only if you are comfortable with the agent keeping a local work-history archive. Avoid using it with confidential projects, personnel matters, credentials, or regulated data unless you first add explicit save confirmation, redaction rules, and cleanup/deletion practices.
The global instruction to store all experience data under /memories promotes blanket retention of potentially sensitive user and workplace information. In this skill's context—career reflection, project summaries, decisions, and lessons learned—that repository can accumulate confidential material over time without scoping, filtering, or lifecycle controls.
The skill explicitly instructs automatic persistent logging of conversation-derived work content in plain terms after important sessions. Because this skill is designed to capture work history and reflections, the stored content is likely to include sensitive corporate context, internal decision-making, or personal performance data, increasing the chance of inadvertent disclosure or over-retention.
The skill directs automatic saving of important work-session details, including decisions, challenges, and reusable techniques, into persistent storage without any privacy notice, consent mechanism, retention limit, or data-minimization rule. In a work-reflection context, those records can easily contain confidential business information or personal data, so silent persistence creates a real data-handling risk.
This markdown file contains user-facing guidance exclusively in Chinese, and nowhere indicates that the skill is region-specific or that users may choose another language. Under the policy rule for language/locale constraints, forcing a specific language without opt-in is a natural-language policy violation.
The description and operating instructions are presented in Chinese, which can amount to a language/locale constraint if the skill effectively assumes Chinese without user opt-in. Under the policy, language restrictions should either be optional for the user or clearly documented as justified and region-specific.
No suspicious patterns detected.
