Back to skill

Security audit

Sidekick Os Pro V2.0

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward Chinese side-income planning helper, with some disclosure gaps around live-market claims and local progress storage.

Before installing, be aware that the skill may ask for personal work, time, budget, and income-goal details, and its tracker can save progress notes locally. Treat its market recommendations as examples unless your agent independently performs current web research, and ask for another language if you do not want Chinese output.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The documented behavior promises real-time market analysis and personalized side-income planning, but the analyzed implementation reportedly only performs local JSON persistence and progress tracking. This mismatch is security-relevant because users may disclose sensitive personal and financial information under false assumptions about how it will be processed, while hidden persistence introduces privacy and trust risks.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill references local scripts and data files, implying file read/write capability, but it does not declare any explicit tool scope or permissions. This creates an authorization ambiguity: an agent or runtime may grant broader filesystem access than users expect, increasing the chance of unintended file access or persistence.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is written as a Chinese-only persona and frames the skill's function entirely in Chinese, with no indication that users may choose another language. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The full skill guidance, workflow, prompts, and examples are all presented in Chinese and do not instruct the agent to adapt to the user's language preference. This can cause the skill to default to a fixed language/locale rather than offering a choice.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file-level documentation states '实时市场分析工具' and '从全网获取最新副业趋势数据', which implies real-time collection from online sources. In practice, get_current_trends returns a static in-code list at L022-L077, so the implemented behavior does not match the claimed live market analysis capability.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This Python file contains user-facing documentation and output labels entirely in Chinese, such as the module description and recommendation text, with no indication that language is configurable or that the skill is intended only for a Chinese-speaking region. The policy requires avoiding forced language or locale constraints unless the user opts in or the constraint is clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This is a natural-language policy concern because the skill’s user-facing description forces a specific language/locale experience with no opt-in or alternative. The file contains Chinese-only titles, docstrings, and task text, but does not indicate that the skill is intentionally region-specific or that users may choose another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring and user-facing descriptions are written entirely in Chinese, and the rest of the skill returns Chinese status and suggestion strings. There is no indication that the skill is region-specific or that users can opt into another language, which conflicts with the language/locale policy described for this audit.

Content

No source excerpt is available for this finding.