Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 扫描目标表由脚本内置（`scripts/scan_skills.mjs` 顶部的 `TARGETS`），是本 skill 扫描范围的单一事实来源：
Security audit
skill-consolidator
Security checks for vulnerabilities and agentic risk
Overview
This skill broadly scans local AI-agent skill/rule files to report conflicts, and its local read/write behavior is disclosed and aligned with that purpose.
Install only if you are comfortable with a tool reading local AI-agent skill/rule files across the listed directories and writing a local report. Use the review-only option when appropriate, and confirm affected paths carefully before allowing any cleanup or consolidation changes.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 当 Node 环境不可用时，按上述扫描范围手工执行：用 Glob 查找各路径的 `SKILL.md` / rules 文件，用 Read 提取 frontmatter 与关键词，按本 skill 定义的冲突类型（同名 / 功能重叠 / 触发词冲突 / 版本差异）检测，手工生成报告。
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
The title and surrounding instructions present the skill primarily in Chinese, and the invocation examples center on Chinese phrasing, without stating that the assistant should match the user's preferred language. This can be a language/locale policy issue when users have not opted into Chinese output.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger conditions are broad enough to invoke the skill during ordinary conversation about skills, plugins, or conflicts, including before installing or recommending a new skill. Because this skill has read/write-capable tools and can scan many local agent directories, over-triggering can cause unnecessary filesystem access and push the session toward unintended cleanup actions.
- Content
Skill Enumeration
Medium
- Category
- Agent Snooping
- Confidence
- 80% confidence
- Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- Content
md 用户确认后允许执行： - 禁用冲突 skill（写入对应工具的配置文件，如 Trae 的 `~/.trae-cn/skill-config.json`）。 - 合并同类 skill：在对应工具的 skills/rules 目录创建主 skill，例如 `MASTER-<category>`（`.claude/skills/MASTER-research/SKILL.md`）。 - 重写 description 以提升区分度；建立"主 skill"映射表。 - 更新本地 skill 目录汇总文件（如 `.trae/skill-registry.md`）。
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 81% confidence
- Finding
The description begins with Chinese text followed by English, which may impose or presume a specific language/locale presentation without documenting user choice or a region-specific reason. Organizational language policy issues apply across all file types when a skill appears to force a language preference without opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The file's descriptive comments, usage notes, and guidance are written in Chinese, and later user-facing report content is also predominantly Chinese. For a general-purpose skill utility, this imposes a specific language/locale expectation without any visible opt-in or alternative language choice.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The generated Markdown report headings, summaries, recommendations, and status messages are emitted in Chinese, with no configuration flag to choose another language. This is a natural-language locale constraint that affects all users of the script and is not presented as an opt-in regional specialization.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The manifest description explains what the skill does, but it does not indicate when the skill should be invoked or what phrases should trigger it. In a manifest file, the absence of trigger scope or exclusion conditions can lead to overly broad or ambiguous activation behavior.
- Content