Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent robot-paper briefing workflow, but it should be reviewed because it can append generated content to an external Feishu document without clear confirmation or target-document scoping.
Install this only if you want a Chinese daily humanoid-robot paper brief and are comfortable with the agent using paper sources and appending to a Feishu document. Before use, specify the exact Feishu document and require approval before each update, especially if implicit invocation remains enabled.
The skill description is broad enough to match generic translation, summarization, or paper-briefing requests, which can cause the agent to activate outside the user's intended scope. Because the skill also contains workflow steps that read additional files and update an external Feishu document, overbroad invocation increases the chance of unintended side effects and misrouting of user tasks.
Forcing Chinese as the default output without clearly presenting it as a user-selectable option can cause the agent to ignore user language preferences or produce output unsuitable for the current context. This is primarily a safety and usability issue, but it can also contribute to accidental skill activation and unexpected behavior when combined with the broad invocation pattern.
The workflow and defaults instruct the agent to append content to a Feishu document, but the skill description does not prominently warn that using the skill may modify an external resource. This creates a real risk of unauthorized or surprising document changes, especially if the skill is auto-invoked from a loosely matching request.
The natural-language instruction explicitly requires producing "a Chinese brief," which imposes a specific language choice on the user. This is a locale/language policy issue because the file does not indicate that the user can choose the language or that the Chinese-only behavior is required for a documented regional use case.
The required pinned header and multiple section labels mandate Chinese content and Chinese length limits, which effectively constrain the skill to a specific language/locale. The file does not indicate user opt-in or explain that this is a justified region-specific skill, so it matches the language/locale policy violation criteria.
The instructions require using the Chinese phrase ⚠️ 待核实 for unverified papers. This imposes a specific language output convention in a general reference file without user opt-in or justification that the skill is intentionally Chinese-only.
The note 今日候选论文较少，已扩展至 72 小时窗口 is prescribed as output text in Chinese. Because the file does not indicate a justified region-specific constraint or let the user choose the language, this conflicts with the language/locale policy.
The instructions mandate 可能为 and 预印本，未经同行评审, both of which force Chinese-language wording in outputs. For a general-purpose sourcing reference, this is a language policy issue unless the skill clearly states it is Chinese-only or asks for user preference.
The template mandates Chinese-language fields and output, including a Chinese title and a sentence limited to Chinese characters. This is a natural-language locale policy issue because it enforces a specific language without any user opt-in or documented justification.
Line L22 states 'Use Chinese for all body text,' which imposes a fixed language requirement. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific; this file frames the reader as primarily Chinese-reading but does not present the language choice as optional.
No suspicious patterns detected.
