Back to skill

Security audit

Jarvis Debt Repayment Tracker

Security checks for vulnerabilities and agentic risk

Overview

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.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:74
Finding

Plaintext Storage of Sensitive Financial Records

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (13)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
89% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
87% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
87% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
85% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

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.

Content

No source excerpt is available for this finding.