Security audit

Cash Flow Forecast Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a descriptive cash-flow helper with no evidence of hidden access, persistence, transactions, or data exfiltration, though its activation scope is broader than ideal.

Installers should understand this is informational finance guidance only, not a substitute for professional advice. The main practical risk is accidental activation from broad keywords or broad finance examples; users should invoke it intentionally for cash-flow forecasting and avoid treating its heuristic recommendations as authoritative financial decisions.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list includes very generic terms such as "cash", "flow", and "assistant", which are likely to match ordinary user conversation and cause unintended invocation of the skill. In a finance-oriented skill, accidental activation can inject irrelevant financial guidance into unrelated chats, create user confusion, and increase the chance that sensitive business context is processed when the user did not intend to use this skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The requirement 'Clear documentation in English' imposes a specific language policy in natural language. Under the policy rules, forcing a specific language without user opt-in or documented justification is a reportable locale/language violation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger section is broad enough to match many ordinary financial-help requests such as budgeting, pricing, taxes, and financial-report interpretation, which creates ambiguous routing and over-invocation risk. Even though the skill is descriptive and non-executable, an overly broad skill can be selected in contexts where specialized, regulated, or more appropriate guidance should be used, increasing the chance of misleading or out-of-scope financial advice.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The top-level docstring describes a generic 'descriptive skill providing templates and frameworks,' while the implementation parses financial indicators and generates tailored cash-flow forecasting recommendations. This is an active contradiction in intent/documentation, not merely omitted detail, because the code is clearly specialized for financial analysis.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest sets the language to "en" with no indication that users may opt into other languages or that the English-only restriction is required for a documented regional or compliance reason. This can violate language or locale policy when a skill imposes a fixed language without user choice.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The comment implies the code is still a placeholder, yet lines immediately following contain active cash-flow-specific recommendation logic for seasonal, growth, and volatile scenarios. This misrepresents the current behavior and intent of the function.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.