Back to skill

Security audit

Investor Education Workflow

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for investor education, but it asks for broad command/write authority and stores customer content persistently without clear consent or sanitization.

Install only in a sandboxed workspace with no unrelated files or secrets exposed. Treat customer questions and feedback as sensitive: require explicit consent before saving, redact personal or account-specific details, and review changes before they enter the reusable knowledge base. Prefer a version that removes Bash/Exec and scopes Write to the investor-education knowledge directory.

Vulnerability Patterns
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • 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 (2)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:8
Finding

Excessive Command-Execution Permissions Violate Least Privilege

Content
View full analysis
Remediation
View remediation

T02 · Agent Memory Poisoning

Warning
Location
SKILL.md:84
Finding

Untrusted Customer Content Is Persisted and Reused Without Sanitization

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 (16)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README presents all user-facing invocation examples, workflow descriptions, and operational guidance solely in Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified or alternatives are offered.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger conditions are overly broad and can activate on many generic explanation or writing requests, causing this skill to run outside its intended scope. In context, that matters because the workflow can perform web access and file writes, so accidental invocation may lead to unnecessary data collection, content generation, or repository modification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The workflow directs the agent to write generated content, customer feedback, and metadata back into local knowledge-base files without requiring explicit user consent. This is dangerous because a user asking only for content generation may unknowingly trigger persistent local state changes, enabling prompt-to-file injection, corruption of the knowledge base, or unauthorized retention of user-provided material.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs storage of customer Q&A, feedback, and usage frequency in a knowledge base with no minimization, redaction, or sensitivity screening. In this context, investor-education conversations can easily contain personal financial details, contact information, or regulated communications, so indiscriminate retention increases privacy, compliance, and data-leak risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description is entirely in Chinese and presents the skill as Chinese-language investor education workflow content without offering any user language choice or noting that the skill is region- or language-specific. Under the policy, language or locale constraints should be opt-in or clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The document is entirely written in Chinese and all example prompts are Chinese-language prompts, which indicates the skill workflow is oriented toward a single language. There is no natural-language indication that users may choose another language or that the locale restriction is intentional and justified for a region-specific tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains user-facing natural-language content exclusively in Chinese, but provides no indication that the skill offers a language choice or that Chinese is a justified locale-specific requirement. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The prompt explicitly routes content to公众号/WeChat publishing ('调用 expression-layer (writes + wechat) -> 交付') without any confirmation, warning, or boundary between drafting and external posting. In an agent workflow, this can cause unintended real-world actions such as publishing content to an external channel when the user may only want drafting assistance, creating reputational and operational risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all instructions and descriptions exclusively in Chinese, and there is no indication that users may choose another language or that the file is intentionally limited to a Chinese-only audience. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file’s natural-language content is entirely in Chinese and presents the prompt/expected behavior only in that language, with no indication that users may choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document presents all instructions and guidance exclusively in Chinese, and there is no natural-language indication that users may choose another language or that the skill is intentionally limited to a Chinese-only audience. This can violate language/locale policy where skills should not force a specific language without user opt-in or explicit justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The document explicitly describes pushing knowledge-base content to 'all related customers' based on advisor usage records and customer FAQ statistics, but it provides no guardrails around consent, audience qualification, opt-out handling, or review for suitability. In an investor-education workflow, broad proactive outreach can create privacy, compliance, and mis-targeting risks, especially if internal usage data is used to drive distribution decisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The entire template is written to require Chinese-language output, including all section headers and content placeholders, but it does not state that language selection is optional or limited to a justified Chinese-only context. This can violate language/locale policy when the skill is used in environments where users have not opted into Chinese output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file frames the prompt and requested article entirely in Chinese and specifies a WeChat public-account publishing context, implying a fixed language/locale. There is no indication that the user can choose another language or that the Chinese-only constraint is explicitly documented as a justified regional requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains user-facing natural-language instructions exclusively in Chinese, including the expected routing behavior and output description. Because no alternative language option or opt-in is mentioned, this may constitute a language/locale policy violation under the requirement to avoid forcing a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all instructional content in Chinese and does not indicate that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.