Ae1
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 核心交付包括:每个岗位技能对应的内化技能知识文档、符合 `assets/specs/agents-skills-specification.md` 的技能目录与 `SKILL.md` 文件,以及已回写技能映射关系的岗位智能体提示词。
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed generator for creating job-specific skill packages from user-provided prompts and knowledge sources, with no hidden execution or persistence behavior found.
Before installing, confirm you are comfortable letting the skill read the specific prompt and knowledge directory or IMA source you provide, and review any prompt file updates before relying on the generated skill packages. Be careful with confidential business material because the skill intentionally summarizes and internalizes source knowledge into new files.
Referenced artifact was not completely inspected
核心交付包括:每个岗位技能对应的内化技能知识文档、符合 `assets/specs/agents-skills-specification.md` 的技能目录与 `SKILL.md` 文件,以及已回写技能映射关系的岗位智能体提示词。
Referenced artifact was not completely inspected
核心交付包括:每个岗位技能对应的内化技能知识文档、符合 `assets/specs/agents-skills-specification.md` 的技能目录与 `SKILL.md` 文件,以及已回写技能映射关系的岗位智能体提示词。
Referenced artifact was not completely inspected
核心交付包括:每个岗位技能对应的内化技能知识文档、符合 `assets/specs/agents-skills-specification.md` 的技能目录与 `SKILL.md` 文件,以及已回写技能映射关系的岗位智能体提示词。
Referenced artifact was not completely inspected
核心交付包括:每个岗位技能对应的内化技能知识文档、符合 `assets/specs/agents-skills-specification.md` 的技能目录与 `SKILL.md` 文件,以及已回写技能映射关系的岗位智能体提示词。
Referenced artifact was not completely inspected
核心交付包括:每个岗位技能对应的内化技能知识文档、符合 `assets/specs/agents-skills-specification.md` 的技能目录与 `SKILL.md` 文件,以及已回写技能映射关系的岗位智能体提示词。
Referenced artifact was not completely inspected
核心交付包括:每个岗位技能对应的内化技能知识文档、符合 `assets/specs/agents-skills-specification.md` 的技能目录与 `SKILL.md` 文件,以及已回写技能映射关系的岗位智能体提示词。
The title and operating instructions are written entirely in Chinese and the skill frames its required outputs in Chinese, but it does not state that language selection is optional or user-configurable. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
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.
### Frontmatter
| Field | Required | Constraints |
| --------------- | -------- | ----------------------------------------------------------------------------------------------------------------- |
| `name` | Yes | Max 64 characters. Lowercase letters, numbers, and hyphens only. Must not start or end with a hyphen. |
| `description` | Yes | Max 1024 characters. Non-empty. Describes what the skill does and when to use it. |
The specification explicitly recommends that skill descriptions include broad user-mention cues such as keywords indicating when to activate a skill, but it does not require counterexamples, exclusion criteria, or narrowly scoped triggers. In an agent ecosystem, this can cause over-broad skill activation and prompt/instruction collisions, increasing the chance that a skill is invoked in inappropriate contexts and influences downstream behavior unexpectedly.
The template’s description field includes a generic invocation placeholder ('Use when users need [触发场景、业务对象、核心动作和输出物]') without enforcing concrete trigger boundaries. In a skill generator, this can propagate into downstream skills that activate too broadly, causing inappropriate routing, overreach into adjacent tasks, or execution without sufficient contextual constraints.
This markdown file contains user-facing instructional content only in Chinese, which effectively forces a specific language for skill authors or operators. The policy allows fixed locale only when the constraint is explicitly justified or when users are offered a choice, neither of which appears here.
This markdown file contains user-facing natural-language instructions exclusively in Chinese, and there is no indication that the user can opt into another language or that the checklist is intentionally limited to a Chinese-language context. Under the language/locale policy rule, forcing a specific language without opt-in is a policy concern.
The file is primarily written in Chinese, but the description template hardcodes the English phrase "Use when users need ...". This creates a natural-language policy risk because generated skills may inherit mixed or English-biased user-facing text without offering a language choice or documenting a justified locale constraint.