Security audit
Security checks for vulnerabilities and agentic risk
This is a Markdown-only response-planning skill with some broad and Chinese-only instructions, but no hidden code, persistence, credential handling, or destructive behavior.
Install this only if you want a Chinese-language meta-skill that changes how the agent structures analysis and explanation depth. Users who prefer explicit invocation or non-Chinese output may find its triggers and language assumptions too broad, but I found no artifact-backed evidence of malicious behavior.
The trigger phrases are broad and generic, including terms like semantic density, adaptive processing, and transparency control, which may appear in unrelated user requests. This increases the chance of unintended invocation, causing the agent to switch into this skill unexpectedly and apply hidden process/state-tracking behaviors outside the user's intent.
Natural-language instructions and descriptions throughout the file force a single language/locale experience, but the file does not state that the skill is region-specific or that users may opt into another language. This can violate language/locale policy when a skill imposes one language by default without user choice.
The skill contains conflicting transparency rules: the description says intermediate process is hidden by default, while the facts discipline requires semantic-density reasoning to be shown to the user. In an agent setting, contradictory disclosure requirements can cause inconsistent behavior, accidental chain-of-thought exposure, or bypass of intended transparency/safety controls depending on which instruction is followed.
The skill content is written as an imperative in Chinese and does not provide any user-language negotiation or fallback, which can force behavior that excludes users who do not read Chinese. In a skill system, this can cause misunderstanding of operational behavior and transparency controls, especially where users need to understand when intermediate reasoning is hidden or revealed.
The document title and all operational requirements are written exclusively in Chinese, with no indication that users may choose another language or locale. Under the policy for natural-language violations, a skill that effectively mandates one language without opt-in should be flagged unless the locale restriction is clearly justified.
This markdown file presents all headings, labels, and instructions exclusively in Chinese, and nowhere indicates that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. The policy explicitly calls out forced language or locale constraints without user opt-in as a natural-language policy violation.
The entire skill exemplar is written in Chinese and all input/output examples prescribe Chinese-language reports, but there is no statement offering a language choice or documenting that the skill is intentionally limited to Chinese users. Under the natural-language policy rules, forcing a specific language without opt-in is a locale-policy concern.
The entire skill exemplar is written as a Chinese-only operating template and does not indicate that users may choose another language or locale. Under the policy, a skill that effectively enforces a specific language without opt-in can be a natural-language policy violation unless the locale restriction is explicitly documented and justified.
This markdown exemplar presents all headings, instructions, and examples solely in Chinese, with no indication that users may choose another language or that the locale restriction is intentional. Under the policy rule for language/locale, forcing a single language without user opt-in can be a natural-language policy violation.
