Security audit

stock-roundtable

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only stock discussion skill that asks the agent to research public market information and present cautious debate, without hidden execution or privileged access.

Install only if you want a Chinese-language, research-heavy stock discussion workflow. Treat outputs as informational, verify cited market data yourself, and do not use generated hold, reduce, stop-loss, or take-profit conditions as the sole basis for trading 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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (10)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The README explicitly frames the skill as suitable for stock analysis, buy/sell/hold decisions, and position adjustment scenarios, but provides no warning that outputs are informational only and may materially influence financial decisions. In an investment-oriented skill, this omission increases the chance that users over-rely on generated analysis as actionable advice, especially when the skill emphasizes deep research and real-time discussion.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The skill is written entirely in Chinese and implicitly expects Chinese-language interaction without offering a user-choice mechanism. This can cause misrouting, misunderstanding of financial nuances, or inaccessible outputs for users in other locales, which is especially risky in an investment context where precision of language materially affects decisions.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger description is extremely broad and matches many common stock-related requests, so this skill may activate in situations where the user did not explicitly ask for a roundtable-style, finance-focused workflow. In a financial-analysis context, overbroad triggering is more dangerous because it can steer ordinary queries into investment-oriented guidance and mandatory web-search behavior, increasing the chance of unintended financial advice or poor routing.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The file is written entirely in Chinese and presents output requirements only in Chinese, without indicating that the skill can adapt to the user's language or that a Chinese-only constraint is intentional. This can cause the agent to ignore user language preference, reducing usability and potentially leading to misunderstandings in investment-related guidance.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This markdown file presents all instructions and examples in Chinese, and nowhere indicates that the user may choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The template explicitly structures output into actionable portfolio guidance such as hold, reduce, stop-loss, and take-profit conditions, but it contains no warning that the content is not financial advice and may be based on incomplete or time-sensitive data. In a stock-analysis skill, users are likely to treat the generated output as personalized trading guidance, increasing the risk of financial harm from overreliance on model outputs.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: This trigger template gives concrete action buckets for continuing to hold, moving to watch status, reducing a position, stop-loss, and take-profit without any accompanying caution about investment risk, suitability, or the need for independent confirmation. Because the skill is specifically designed for stock debate and position-management questions, the absence of safeguards makes it more likely that users will act on generated thresholds as if they were reliable financial instructions.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The document is written entirely in Chinese and includes instructions such as prioritizing mixed Chinese-English keywords, but it does not offer users any language or locale opt-in. Under the policy, natural-language content that enforces a specific language without user choice can be a locale-policy violation.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: The user-facing description is written in Chinese and does not indicate that language is optional or that the skill is intentionally limited to Chinese-speaking users. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 85% confidence
Finding: This markdown file contains user-facing instructions exclusively in Chinese, which can constitute a language/locale policy issue if the broader environment expects language choice or neutrality. There is no opt-in, alternative language option, or justification that the skill is region- or language-specific.

Static analysis

No suspicious patterns detected.