Security audit

元器件选型与替代料顾问

Security checks for vulnerabilities and agentic risk

Overview

The skill is a detailed electronics part-selection advisor, and its sensitive data guidance is disclosed and bounded rather than hidden or abusive.

Use this for electronics sourcing and substitution review. Expect Chinese-language workflow text and web/PDF lookups. Only connect internal BOM, inventory, or transaction databases on systems where the user is authorized, and keep the skill's own rule of not outputting internal prices, supplier names, customer names, stock counts, contracts, or order details.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (25)

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.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list includes broad everyday terms such as 'BOM', '规格书', '交期', and '问价', which can plausibly appear in normal conversation outside the intended specialist workflow. Over-broad activation can route unrelated user requests into this skill, causing unintended disclosure-oriented questioning, irrelevant procurement guidance, or bypass of more appropriate skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: 整个技能描述与输出模板均固定为中文，且未说明可根据用户偏好切换语言。按规则，若技能在自然语言层面强制特定语言而无用户选择或明确的合理地域限定，属于语言/locale 策略问题。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The entire skill documentation is written in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without user 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: 93% confidence
Finding: Natural-language policy review applies to all file types. The registry uses Chinese-only display strings and operational guidance, which can impose a specific language/locale on users or operators without any opt-in mechanism or stated region-specific justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This JSON manifest contains a user-facing display value set to Chinese only ("连接器") with no indication that language is selectable or limited to a China-specific deployment context. The policy for this audit flags language/locale constraints when a skill appears to force a specific language without user opt-in or clear justification.
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: 91% confidence
Finding: This manifest/config file contains user-facing labels in Chinese, such as the display name, and the remainder of the file consistently defines outputs, wording, and reporting text only in Chinese. Because the file provides no opt-in, alternative locale, or documented region-specific justification, it may violate language/locale policy by forcing a specific language.
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: 91% confidence
Finding: This JSON category file consistently defines display text, workflow steps, notes, and required output wording in Chinese, including mandated report phrasing and status labels. Under the policy rule for natural-language violations, forcing a specific language without opt-in is a finding unless the locale restriction is explicitly documented and justified, which is not present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The title, descriptions, rules, and labels throughout the manifest are written exclusively in Chinese, indicating a fixed language requirement. The file does not offer a language choice or document a region-specific justification, which matches the policy criterion for language/locale violations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: All user-facing descriptive phrases and policy text in the file are fixed in Chinese, with no indication that users may choose another language or that the locale restriction is intentionally limited to a China-specific workflow. The rule requires flagging language/locale constraints when they are imposed without opt-in or documented justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all operational instructions exclusively in Chinese and does not indicate user opt-in, multilingual support, or a documented region-specific justification for the language constraint.
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: 96% confidence
Finding: This markdown skill reference is written entirely in Chinese and does not indicate that users may choose another language or that the restriction is limited to a China-specific or otherwise locale-bound workflow. Under the policy, forcing a specific language without user 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: 82% confidence
Finding: This skill file is written entirely in Chinese and presents the policy content as mandatory instructions without indicating that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
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: 88% confidence
Finding: The entire skill standard is written as mandatory operational guidance in Chinese, using prescriptive language such as '必须' and '禁止', but nowhere offers users a language/locale option. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
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.

Whitespace Padding

Medium

Category: Prompt Injection
Confidence: 70% confidence
Finding: Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
Content: Scanner excerpt · references/power-pin-to-pin-judgment.md (reported line 105)May include surrounding context.
md
**"改板能否达成对应"的取值口径**：机器判不出飞线能否救，须由判定者按下列三态声明（缺数据填「未判定」，不得留空）： | 取值 | 含义 | 出口 | | ------- | --------------- | -------------------------------------------------------------------------------------------------- | | **可行** | 经改板 / 飞线可达成功能对应 | **改板方案**（§2.2），不套用 PM 档位 | | **不可行** | 改板亦无法达成对应 | **PM-B** |

Whitespace Padding

Medium

Category: Prompt Injection
Confidence: 70% confidence
Finding: Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
Content: Scanner excerpt · references/power-pin-to-pin-judgment.md (reported line 108)May include surrounding context.
md
| 取值 | 含义 | 出口 | | ------- | --------------- | -------------------------------------------------------------------------------------------------- | | **可行** | 经改板 / 飞线可达成功能对应 | **改板方案**（§2.2），不套用 PM 档位 | | **不可行** | 改板亦无法达成对应 | **PM-B** | | **未判定** | 尚未评估 | **⚠️ 未判定**（同通用 PPJ §6.0：**不套用任何 PM 档位**，走 §6.1「⚠️ 未判定 → 需评估」行）。**须由原判定者补充输入后重跑，或路由 L2 工程师分流后方可定档** | > **「未判定」不等于 PM-B**：与通用 PPJ §6.0 一致，输入缺失时不得输出 PM-A / PM-B / PM-C 任一档，只落「需评估」，须索取后重跑。

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.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: This is a JSON manifest file, so vague-trigger review applies. The instruction '新增品类 = 复制任一品类文件...并在本数组追加一条' is broad procedural language that could be interpreted as a generic action path for any new category, but it does not define constraints, exclusions, or negative examples for when that workflow should not be used beyond the later runtime caveat.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: This JSON manifest-like file describes the mapping's purpose and prohibitions, but it does not define any explicit activation conditions, scope boundaries, or negative examples for when the skill should or should not be invoked. For manifest-scope review, that absence can make triggering context ambiguous if this description is used operationally to determine applicability.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The document is written entirely in Chinese and all prescribed output phrasing examples are Chinese-only, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.