Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local reply-writing helper with Chinese-focused style presets and no evidence of credential use, persistence, remote code, or hidden side effects.
Install this if you want Chinese-focused, preset-style reply drafting. For non-Chinese contexts or channels other than WeChat, explicitly tell the agent the desired language and channel before using it.
Referenced artifact was not completely inspected
- `node scripts/showcase-replies.mjs --scene reject-request --intent "礼貌拒绝继续无偿帮忙" --persona trusted-advisor --mode clear-reject`
The skill states in Chinese that it generates replies for users, effectively constraining behavior toward Chinese-language output without offering language selection or documenting a locale limitation. This can cause incorrect-language responses, user confusion, or policy/compliance mismatches in multilingual deployments, though it is primarily a reliability and usability issue rather than a direct security exploit.
The trigger conditions are very broad phrases like 'help me reply with high EQ' or requests to make text 'more tactful' or 'more executive,' which are common in everyday conversations. In an agent environment, this can cause the skill to activate unexpectedly on many unrelated user prompts, leading to unnecessary instruction injection, altered responses, or priority conflicts with other skills.
The manifest’s default prompt says "Use $reply-styles to rewrite this message in a polished high-EQ tone," but it does not define when this skill should or should not be invoked beyond a generic rewrite request. This can overlap with common editing or drafting requests and lacks negative examples or tighter trigger constraints.
This markdown file contains user-facing example prompts and scenario descriptions exclusively in Chinese, which effectively imposes a specific language on users. The policy for SQP-3 allows locale constraints only when the skill offers user choice or clearly documents a justified region-specific limitation, neither of which appears here.
The content is written as an instruction in Chinese and presents the channel guidance entirely in that language, with no indication that users may opt into another language or locale. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is clearly documented and justified.
This markdown file presents all substantive operating guidance in Chinese and does not indicate that language selection is optional or limited to a justified region-specific use case. The policy requires flagging language or locale constraints when a skill forces a specific language without user opt-in.
This markdown rubric is written entirely in Chinese and assumes Chinese-language output norms without offering any language or locale choice. The policy requires flagging language or locale constraints when a skill effectively forces a specific language without explicit user opt-in or justification.
The file defines the intensity system entirely in Chinese and does not provide any user language choice, fallback, or documented locale restriction. In a model-agnostic reply-writing skill, this can cause the agent to default to Chinese outputs or internal style instructions even when the user expects another language, creating reliability and safety issues through misunderstanding, inappropriate tone, or unusable responses in customer-facing contexts.
The document is written entirely in Chinese and presents reply modes and usage guidance only in Chinese, with no indication that users may choose another language or locale. This creates a natural-language policy concern because it effectively constrains interaction language without documented opt-in or justification.
The document’s instructions and labels are presented entirely in Chinese, including guidance on how the persona packs should be used, without offering an alternative language or stating that Chinese is optional. Under the policy for natural-language violations, a forced language or locale without user opt-in is a reportable issue.
The scenario labels and instructions are presented only in Chinese, which effectively forces a specific language for users of this skill artifact. The policy explicitly calls for flagging language or locale constraints unless the skill offers opt-in or clearly documents a justified region-specific limitation.
The usage guidance says '先根据场景和关系选风格，再写回复。', which directs the responder to write replies in Chinese by default. This is a language policy issue because the file imposes a specific language without indicating user choice, opt-in, or a justified region-specific constraint.
This markdown file presents all user-facing examples and labels in Chinese, which can amount to forcing a specific language without user opt-in. The policy allows locale constraints when they are explicitly justified, but this file does not document such a justification or offer alternatives.
This code sets the default output channel to "wechat", which implies a specific platform/locale preference when the user does not provide one. Under the language/locale policy rule, hard-coding a locale-specific default without explicit user choice can be a natural-language policy issue.
This code file embeds style labels, sample openings/closings, preferred words, and guidance primarily in Chinese, effectively constraining generated output toward a single language/locale. The file does not indicate that Chinese is optional or user-selected, which matches the policy concern for forcing a specific language without opt-in.
The code sets the default channel to "wechat", which implies a specific locale/platform preference unless the user explicitly overrides it. This can be a natural-language policy concern because it enforces a default communication context without clear user opt-in or justification in the file.
No suspicious patterns detected.