Back to skill

Security audit

A股交易助手 stock bitsoul

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned stock performance calculator that discloses its token and stock-data network dependency, with privacy and trigger-scope caveats users should understand.

Before installing, understand that using stock-code/date mode may send stock symbols, date ranges, and related financial query details to the declared external stock-data service using your BITSOUL_TOKEN. Use the direct capital-input mode if you do not want remote stock-data lookup.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs use of a BITSOUL_TOKEN and a remote stock-data service but does not clearly warn users that requests and possibly financial query details will be transmitted to an external service. In a finance-related skill, this is more sensitive because user prompts may contain holdings, transaction timing, and strategy information that can reveal personal investment behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match ordinary financial conversation, which can cause the skill to activate when the user did not explicitly intend to invoke a stock-analysis workflow. In this skill’s context, unintended activation may send user-supplied stock symbols, dates, or investment details into the skill logic and associated remote data flow, creating privacy and consent issues rather than direct code-execution risk.

Content

No source excerpt is available for this finding.