Security audit

my_stock_decide_skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed stock-decision workflow that handles sensitive portfolio data but does not install code, persist access, execute trades, or hide unrelated behavior.

Before using this skill, only upload portfolio screenshots you are comfortable sharing with the agent and remove account numbers, names, and other identifiers where possible. Treat its output as decision support, not automatic trade execution or personalized financial advice from a regulated adviser.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill mandates real-time web/API queries and stepwise reporting while operating on a user's portfolio context, but it provides no warning, consent boundary, or minimization guidance for transmitting sensitive financial information to external services or linked skills. In a trading-decision skill, holdings, assets, and watchlist symbols can reveal net worth, strategy, and risk posture, so silent onward transmission meaningfully increases privacy and confidentiality risk.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill explicitly instructs extraction of holdings and total asset information from user-supplied images, which is highly sensitive financial data, yet it includes no safeguards about retention, redaction, or disclosure to downstream tools. Because image-based account snapshots often contain account numbers, balances, names, and broker details, this context makes accidental over-collection and external exposure more dangerous than generic OCR.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The natural-language description and operational instructions are written to require Chinese-language behavior, but the skill does not state that language selection is user-configurable or that the skill is intentionally region/language-limited. This can violate language/locale policy when a skill effectively forces a specific language without opt-in.
Content: No source excerpt is available for this finding.