Security audit

research-quality-gate

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only research review skill with coherent behavior, though its license metadata and broad trigger keywords should be cleaned up.

Install only if you are comfortable with a mostly Chinese research-review workflow. Treat its licensing as unclear until the publisher resolves the MIT versus All Rights Reserved conflict, and consider narrowing trigger keywords before using it in a multi-skill environment.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.
md
| 文档与理论文本 | 本 `SKILL.md`、`README.md`、其中「理论依据」段与一切理论表述 | **不在 MIT 覆盖范围内**：保留所有权利（All rights reserved） |

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file presents the critical scope notice and licensing carve-out in Chinese, while the rest of the MIT license is in English. This creates a language/locale policy concern because important usage restrictions are conveyed in a specific language without opt-in or an explicit justification that the skill is region-specific.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords are generic terms such as research, quality, and gate, which can cause the skill to activate in unrelated conversations. Unintended invocation can inject this skill's workflow into tasks where it does not belong, increasing prompt-routing errors, wasting resources, and potentially biasing outputs in multi-skill environments.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The file presents contradictory licensing terms: the front matter claims MIT while later sections state the package is purely documentation/theory and entirely All Rights Reserved. This creates legal ambiguity that can mislead downstream users, repositories, or automated agents into reusing content under permissions that are later denied, exposing operators to compliance and supply-chain governance risk.
Content: No source excerpt is available for this finding.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This file contains operational skill documentation and guidance, but it forces a specific language/locale for readers with no opt-in or alternative. Under the policy, language restrictions are a natural-language violation unless the skill offers a choice or clearly justifies the locale constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The manifest description is entirely in Chinese, which imposes a specific language/locale on users without indicating any opt-in, alternative language support, or region-specific justification. This matches the policy category for language or locale constraints expressed in natural language.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.