Security audit

Financial Equity Research

Security checks for vulnerabilities and agentic risk

Overview

This skill provides financial research report workflows and does not include hidden code, persistence, credential access, or destructive behavior.

Install this as a research assistant, not as financial advice automation. Be aware that a few broad trigger phrases may invoke market-research workflows when finance context is unclear, and review any generated trade ideas, target prices, or model updates before relying on them.

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
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 (5)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger set for the idea-generation skill includes very generic phrases such as "find ideas," "new ideas," and especially "pitch me something," which can match ordinary conversation rather than an explicit request to run this financial screening workflow. That creates a prompt-routing vulnerability where the skill may be invoked unintentionally, causing the agent to enter an investment-research workflow the user did not mean to trigger.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The morning-note skill advertises broad trigger phrases like "what happened overnight" and "trade idea," both of which are common in normal conversation and not uniquely tied to this specific skill. This increases the risk of accidental invocation, misrouting benign chat into market-analysis behavior and potentially producing unintended financial output.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The document presents section headings and explanatory text in Chinese while most operational content is in English, but it does not explain whether language follows user preference. This can create a language-policy issue because the skill implicitly imposes a locale/language style without documenting user choice.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The phrase "what happened overnight" is particularly ambiguous because it can refer to personal events, system activity, news, or markets. In a skill-based agent, this ambiguity can cause unintended activation of the morning-note workflow when the user is not requesting financial analysis.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: A generic trigger such as "analysis" or similarly broad wording in the sector-overview skill can collide with many ordinary requests that are not asking for a sector landscape report. This weakens routing precision and can cause the agent to invoke a heavyweight research workflow without clear user intent.
Content: No source excerpt is available for this finding.