T09 · Insecure Skill Coding Practices
- Location
SKILL.md:74- Finding
Plaintext Storage of Sensitive Financial Records
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This finance tracker appears purpose-aligned, but it should be reviewed because it stores sensitive income and debt details in plain local files and can activate on broad finance terms without clear consent controls.
Review this before installing if you may enter real income, expense, debt, bank, or payment information. Use it only with explicit commands, keep the generated Markdown files in a private protected location, avoid raw credentials or API tokens, and delete or secure old records when no longer needed.
SKILL.md:74Plaintext Storage of Sensitive Financial Records
The activation keywords are very broad, common financial terms that are likely to appear in ordinary conversation, which can cause the skill to trigger unintentionally. Because this skill handles personal finance and debt tracking, accidental activation could capture sensitive financial context, create unwanted records, or expose private information through responses or automations.
The trigger list uses very broad finance-related keywords that are common in ordinary conversation, which can cause the skill to activate unintentionally. Because this skill handles sensitive financial and debt data, accidental activation increases the chance of collecting, displaying, or writing private information when the user did not explicitly intend to use this skill.
The activation rule says the skill activates whenever the user 'mentions' listed topics, which is ambiguous and overly permissive. In a financial skill, this raises privacy and integrity risks because normal discussion about money, debt, or savings could trigger file updates or expose stored financial summaries without explicit user consent.
The skill stores detailed income, expense, and debt information in local files but does not warn users that highly sensitive financial data will be persisted. Users may provide personal financial details without understanding retention, exposure, or local-access risks, which is especially concerning for debt and repayment information.
Mentioning bank statement import and payment platform API connectivity without privacy or credential warnings normalizes future handling of highly sensitive account data. Even as an extension feature, this can lead users to share statements, tokens, or credentials without understanding the security implications.
The user-facing README content and activation instructions are presented only in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy where user choice or documented justification is expected.
The trigger '收入' is extremely short and broadly applicable, making unintended activation likely in normal conversation. In this skill's context, even low-friction accidental activation matters because the skill deals with sensitive personal finance records.
The trigger '记账' is short and common enough to match benign discussion, increasing the chance of misfires. Since the skill may log or retrieve personal financial information, accidental invocation creates avoidable privacy and data-integrity risk.
The trigger '还债' is brief and may activate on general discussion about debt repayment rather than a clear request to use the skill. Because debt information is sensitive, unintended activation could reveal status summaries or lead to incorrect updates.
The trigger '收支' is short and semantically broad, so it may match many ordinary financial discussions. In a skill that handles stored financial data, such broad matching creates a real but lower-severity risk of accidental access or updates.
The trigger '财务' is a generic topic term rather than a deliberate command, so it is prone to unintended matches. Given this skill's ability to manage sensitive budgeting and debt data, the broad trigger increases privacy risk even if exploitation is indirect.
The trigger '存款' is short and can appear in many benign contexts, making accidental activation plausible. While lower severity than direct credential exposure, it still matters because the skill may handle or surface sensitive financial records.
The package description is written only in Chinese ("自动化每日收入追踪与债务管理系统"), which imposes a specific language on users without offering any language or locale choice. The policy explicitly calls for flagging language or locale constraints unless the skill offers opt-in or clearly documents a justified region-specific limitation.