Back to skill

Security audit

Portfolio Risk Allocation Reviewer

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only portfolio review workflow; its main issue is broad implicit triggering, not hidden or unsafe behavior.

Before installing, be aware that this skill may trigger on broad finance or operations phrasing. Use it intentionally for portfolio-review workflows, avoid uploading more brokerage data than necessary, and verify any investment output with qualified financial judgment.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (12)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation examples do not clearly define the skill's scope and include vague phrases like 'Help me' and 'I need a practical workflow,' which are common across many benign requests. Because this skill handles financial analysis context, ambiguous routing increases the chance of misapplication, overcollection of sensitive portfolio data, or users receiving financial-review output when they did not intend to invoke this specialized workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger sentence is extremely broad and malformed, making accidental or unintended activation more likely when a user asks for generic help. In an agent ecosystem, ambiguous triggers can route unrelated financial questions into this skill, causing inappropriate portfolio guidance or disclosure of brokerage data to the wrong workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough to activate on common finance and operations requests without clearly requiring brokerage-export or portfolio-risk-review context. In an agent system, ambiguous activation boundaries can cause unintended invocation, routing user data into the wrong skill, and producing misleading investment-related guidance in contexts where it was not requested.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description uses broad activation terms like 'business-and-operations' and generic requests for 'analysis' or 'implementation support,' which can cause the skill to trigger for many unrelated finance or operations prompts. Overbroad invocation can route users into an investment-oriented workflow when they did not request it, increasing the chance of irrelevant or risky financial guidance being surfaced inappropriately.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger section defines ambiguous keywords and example triggers without any exclusion criteria, so the skill may activate on commonplace finance language such as 'risk review' or 'rebalancing' even when the user's request is outside portfolio analysis. In a financial context, misrouting is more sensitive because it can lead to unsuitable investment-oriented outputs or advice on incomplete facts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description and activation guidance are broad enough to match common business or portfolio-related requests that may not actually need this specialized skill. Overly broad routing can cause unintended invocation, leading the agent to apply domain-specific workflows in the wrong context and potentially produce irrelevant or misleading financial analysis.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The keyword list contains generic phrases such as business-and-operations and risk review, which are likely to overlap with many unrelated user requests. This increases the chance of accidental skill activation, causing misrouting and potentially untrusted handling of sensitive financial tasks under assumptions the user did not intend.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The default prompt uses broad, everyday phrasing such as helping with investor/advisor workflows and practical support, which overlaps with common finance-related requests. In combination with implicit invocation, this broad language can make the skill activate unexpectedly and shape responses in situations where the user did not intend to request portfolio-risk analysis.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill enables implicit invocation without any visible activation boundaries, eligibility rules, or narrowing conditions. That can cause the agent to trigger on loosely related finance questions and introduce unrequested portfolio-analysis behavior, increasing the chance of inappropriate data handling or over-broad tool use in sensitive investment contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger sentence begins with a very generic phrase ('Help me') and then appends the requirement text, which creates a broad and ambiguous activation condition. Overbroad triggers can cause the skill to be invoked for loosely related conversations, leading to unintended routing, user confusion, and possible exposure of financial-analysis workflows in contexts where they were not requested.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The sentence 'I need a practical workflow for ...' is still broad enough to match many ordinary requests without clearly limiting invocation to portfolio allocation and brokerage-review scenarios. In an agent system, ambiguous routing phrases increase the chance of accidental skill activation, which can mis-handle user intent and produce inappropriate financial guidance workflows outside the intended scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This file is a Chinese-language README and presents the skill content entirely in Chinese, while also referencing separate English documentation. There is no explicit statement that users may choose their preferred language here, which can be a language/locale policy concern unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.