Security audit

Local MiniGPT

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent local mini-model training/demo toolkit with optional, disclosed web and dataset downloads, not a hidden or destructive capability.

Install only if you are comfortable with a Chinese-language toolkit that can optionally contact public search engines and dataset mirrors. Avoid putting secrets or private text into search queries, and pass explicit output directories in your workspace for checkpoints and generated data.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (18)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 94% confidence
Finding: The skill advertises and instructs use of capabilities that imply local file reads/writes and outbound network access, but it does not declare any explicit tool scope or permission boundary. This creates an authorization mismatch: an agent or reviewer cannot easily determine the intended limits of filesystem and network behavior, increasing the chance of over-broad access, unsafe execution, or silent data exfiltration when handling user corpora or web search.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill metadata description is entirely in Chinese and presents the skill's purpose, triggers, and constraints only in that language. This creates a language/locale policy concern because users are not offered an alternative language or any opt-in choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This code includes natural-language instructions and status output entirely in Chinese, which imposes a specific language on users. The policy allows locale constraints only when users are given a choice or when the constraint is clearly documented and justified; neither is present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The module docstring, argument descriptions, and runtime prompts are written in Chinese only, which imposes a specific language on users. The file does not provide an opt-in, alternative locale, or documentation showing that this skill is intentionally region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The module docstring, usage explanation, argument descriptions, and runtime messages are written in Chinese only. This effectively forces a specific language for interaction and explanation, with no option for users to choose another locale or language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: This code file contains natural-language strings that force a specific language/locale for usage instructions and runtime output. Under the policy, a skill should not impose a language without user choice unless the locale restriction is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The module docstring presents the skill description and usage entirely in Chinese, and user-facing status/output strings throughout the file are also Chinese-only. This creates a locale/language constraint without offering the user a choice or documenting that the skill is intentionally region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This code includes natural-language instructions and output text in Chinese, which imposes a specific language on users without any opt-in or alternative. The policy explicitly flags language or locale constraints when they are forced rather than user-selectable or clearly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The module docstring and command usage are written only in Chinese, which imposes a specific language on users without offering a locale choice. This matches the policy category for language or locale constraints that are not optional or explicitly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: Argument parser descriptions and help strings are hard-coded in Chinese, and the script does not provide any user opt-in or language selection. This is a natural-language policy concern because it forces a specific language for interaction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This code file contains natural-language strings in Chinese in the module docstring and CLI description, which effectively fixes the skill's user-facing language. The policy for this category flags language/locale constraints when they are imposed without user choice or explicit justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The hardcoded Accept-Language header forces a Chinese locale preference without user choice, which leaks a regional/language preference to every external search engine request. This is primarily a privacy and transparency issue rather than a direct compromise vector, but it can affect profiling, content shaping, and user expectations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The script sends the user’s raw search query to third-party search engines (DuckDuckGo, Bing, Baidu), which discloses potentially sensitive user input to external services. In the context of a local-AI helper tool, users may reasonably assume data stays local, so undisclosed outbound transmission creates a real privacy risk even though it is expected for a web-search feature.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The file's natural-language content is entirely in Chinese, including the top-level module description and later explanatory comments/docstrings. Under the policy, forcing a specific language without user opt-in can be a locale/language policy violation, and this file does not indicate any optional language support or a justified region-specific constraint.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The script sends the user's query to an external search function without any explicit runtime disclosure or consent prompt in this file. While this appears to be part of the documented demo behavior rather than covert exfiltration, user queries may still contain sensitive text and are transmitted off-box, creating a privacy risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This code contains user-facing natural-language strings in Chinese, including the module docstring, assertion messages, and the final print output. Under the policy rule, forcing a specific language without user opt-in can be a locale-policy violation when no choice or justification is provided.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The module docstring and class/method documentation are written in Chinese, which creates an implicit language constraint for users or maintainers who rely on inline natural-language instructions. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation when no alternative or choice is provided.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file's primary natural-language documentation is written entirely in Chinese, including the module docstring and explanatory comments. This imposes a specific language on users and maintainers without any indication that language choice is optional or that the skill is region-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.