Security audit

双色球算法选号防被骗 · 理性选号助手 + 防割韭菜盾

Security checks for vulnerabilities and agentic risk

Overview

The skill is a lottery analysis/reporting tool, but it asks for privileged scheduled execution and can read or write across local user profiles, so it needs careful review before installation.

Use this only under a normal user account and avoid creating the SYSTEM/highest scheduled task. Treat the WorkBuddy integration, peer-install mirroring, and optional local server as high-impact features that should be disabled or reviewed first; offline/manual use of python run_ssq.py is much safer.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (4)

T06 · System Persistence

Error

Location: operations.md:106
Finding: Highest-Privilege SYSTEM Scheduled Task Persistence
Content: View full analysis
Remediation: View remediation

T05 · Unauthorized Access and Privilege Escalation

Error

Location: ssq_healthcheck_all.py:133
Finding: Cross-User WorkBuddy Database Enumeration and Access
Content: View full analysis
Remediation: View remediation

T05 · Unauthorized Access and Privilege Escalation

Error

Location: ssq_smart.py:340
Finding: Cross-User Modification of Peer Skill Installations
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: ssq_serve.py:91
Finding: Directory Traversal in the Optional Local Report Server
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (230)

Context-Inappropriate Capability

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The documented ability to modify Windows scheduled-task settings is unrelated to the user-facing purpose of lottery randomness education and materially expands the skill's control over the host environment. Any agent that can alter scheduler behavior can weaken safeguards, persistence settings, runtime context, or execution conditions, which creates a real host-level integrity and persistence risk if invoked outside strict boundaries.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 90% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 88% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: Searching local files for reports and validating expected HTML sections is mostly internal QA behavior, not a direct security flaw. It is still a scope mismatch and contributes to overbroad package behavior, but the standalone risk is limited compared with the network/server/scheduler issues.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.