Security audit
Security checks for vulnerabilities and agentic risk
This is mostly a Zhang Yiming persona/advice skill, but it quietly performs git-based update checks and can activate on broad phrases, so it should be reviewed before installation.
Install only if you are comfortable with a Chinese-language persona skill that may trigger broadly and use web search for factual questions. Review or remove the silent version-check section if you do not want the agent reading git metadata, contacting the git remote, or writing `.last-update-check` during normal use.
The activation phrases are extremely broad, including generic references like '字节怎么看', '一鸣怎么选择', and even '一鸣', which can cause accidental triggering in unrelated conversations. Because the skill then enforces strong roleplay and hidden workflow behavior, unintended activation can override user intent and indirectly trigger unnecessary tool-use or policy-shaping behavior.
The entire skill is written to operate in Chinese and instructs the agent to answer in a specific persona and style, but it does not state that this is a Chinese-only skill or allow the user to choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly documented and justified.
This persona/advisory skill instructs the agent to inspect local repository state, query the git remote, and write a timestamp file, which exceeds the minimum capability needed for answering perspective questions. That creates unnecessary filesystem and network side effects, and could leak repository metadata or normalize hidden tool use unrelated to the user’s request.
Requiring git-based remote version checks for a roleplay/persona skill is unjustified and grants an unnecessary external communication path. Even if the commands are limited, they can reveal repository origin details, create unexpected outbound traffic, and expand the attack surface for a skill whose stated purpose is purely conversational analysis.
This markdown file contains user-facing natural language entirely in Chinese and does not indicate that the skill or document is intentionally limited to Chinese-speaking users or a China-specific context. Under the language/locale policy rule, forcing a single language without opt-in can be a policy concern.
SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all substantive instructions and analysis in Chinese, but does not indicate that the skill is China-specific or offer an opt-in or alternative language, which can conflict with a policy requiring user language choice.
This markdown file presents all instructions and reference material in a single language and does not indicate that Chinese is optional or required for a specific regional context. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.
This markdown file is entirely framed in Chinese from the title onward, with no indication that alternative languages are supported or that the language choice is optional. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.
SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all substantive instructions and content in Chinese only, with no indication that the user opted into that language and no documented region-specific requirement justifying the constraint.
No suspicious patterns detected.
