Security audit

traceability-audit-team

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-based audit helper with no executable payload, but users should keep its file-writing ability limited to separate report outputs.

Install only if you want a Chinese-first traceability and evidence-audit workflow. When using it, direct the agent to write only new audit reports or checklists, not to edit original evidence, logs, credentials, or source materials.

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

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (13)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 100)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 begins with an organizational notice written in Chinese, while the rest of the license text is in English, and there is no indication that users may choose their preferred language or that the Chinese-only notice is required for a region-specific purpose. This can constitute a natural-language locale policy issue because key licensing conditions are presented in a single language without opt-in or documented necessity.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill is described as a traceability and evidence-audit tool, which is inherently a read-focused workflow, but it declares Write capability without any documented need for modifying state. In a security-sensitive audit context, unnecessary write access increases the risk of evidence tampering, accidental alteration of source material, or creation of misleading audit artifacts.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The boundary section explicitly promises that the skill will not alter any materials, but the manifest still includes Write permission. In the context of a provenance and evidence-verification skill, this contradiction is especially dangerous because write access could be used to modify the very records being audited, undermining integrity and chain-of-custody assumptions.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill documentation states the package has no code and is purely documentation/theory, yet the manifest grants executable tool capabilities including Write. This mismatch can mislead users and reviewers into assuming the skill is read-only, while it actually has the ability to modify files or artifacts in the host environment.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The skill metadata is entirely written in Chinese and presents the skill as a Chinese-language experience, but it does not indicate that users may choose another language or that the locale restriction is intentional and justified. Under the policy, forcing a specific language without opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest includes a long trigger list with broad, generic terms such as '溯源', '审计', and 'AI 身份', which can cause the skill to activate in contexts far beyond its intended scope. In a security- or evidence-oriented skill, unintended activation is risky because it may inject authoritative-seeming audit or attribution guidance into unrelated conversations, increasing the chance of user confusion or misuse.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill metadata and descriptive content are entirely in Chinese, including the displayed name and all evaluation dimension labels/notes. There is no indication that users can choose another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific context, which may conflict with language/locale choice expectations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: SQP-3 applies to all file types and covers natural-language policy violations such as forcing a specific language without user opt-in. This template presents all headings and instructions only in Chinese, with no indication that users may select another language or that the template is intentionally limited to a Chinese-speaking context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This file contains user-facing natural-language instructions solely in Chinese, which can constitute a language/locale policy issue when no opt-in or scope limitation is provided. The content does not indicate that the skill is intended only for Chinese-speaking users or a China-specific compliance context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This markdown file contains only Chinese-language instructions and content, with no indication that users may choose another language or that the locale restriction is intentional. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This SVG contains all user-facing labels in Chinese, including the title and axis/legend text, with no indication that the skill is intentionally region-specific or that another language is available. That can violate the language/locale policy because it imposes a specific language without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: 该文件是面向技能审计结果的自然语言文档，但全文仅以中文呈现，没有提供用户语言/地区选择，也未说明该技能或报告仅面向特定中文使用场景。根据语言/locale 政策，强制单一语言且无用户选择可能构成自然语言策略违规。
Content: No source excerpt is available for this finding.