Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Chinese web-novel writing helper that writes only local project files when asked, with no evidence of hidden network access, credential use, or persistence outside the workspace.
Install this if you want a Chinese web-novel workflow with local project files. Use --clean only when you intentionally want to restart generated output, because it removes prior generated chapters and output markdown in the current workspace.
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
if [ "$CLEAN" = true ]; then
log_step "清除旧的输出文件..."
rm -rf "$CHAPTERS_DIR" 2>/dev/null || true
rm -f "$OUTPUT_DIR"/*.md 2>/dev/null || true
mkdir -p "$CHAPTERS_DIR"
log_step "重置记忆文件..."
The skill metadata and body consistently instruct the agent to generate Chinese-language novel content, which can override or ignore a user's preferred language if the runtime selects this skill automatically. This is not a code-execution issue, but it is a real policy/quality vulnerability because it can cause unwanted behavior, reduce accessibility, and make downstream outputs inconsistent with user intent.
The skill metadata and default prompt hard-code Chinese-language output without indicating that this should depend on the user's preference. This can override user intent, reduce accessibility, and create misleading or unusable outputs when the requester expects another language, making it a genuine prompt-safety and UX policy issue rather than direct code-execution risk.
This markdown template is entirely written in Chinese and presents all section headings, labels, and usage instructions in a single fixed language. Under the policy, a skill should not force a specific language or locale unless it offers user opt-in or clearly documents that the constraint is justified for a region-specific use case.
The file title and core instruction are written as a fixed Chinese prompt-generation template and direct the system to complete user input using this template. There is no indication that users may choose another language or locale, which can constitute a language-policy violation under the natural-language policy rules.
The document is entirely written as a normative guide in Chinese and frames the skill's behavior as expanding a user's input according to these instructions, with no indication that users may opt into another language or locale. This can constitute a language/locale policy violation because it implicitly forces a specific language without documented user choice or region-specific justification.
This shell script’s comments, usage text, status messages, and workflow instructions are consistently written in Chinese, which effectively forces a specific language for users interacting with the skill. The file does not offer any language/locale selection or document a justified region-specific limitation.
SQP-3 applies to all file types and covers language or locale policy violations. This reference file presents all guidance only in Chinese and does not indicate user opt-in, alternative language availability, or a justified region-specific scope.
This markdown file presents all headings and instructions in Chinese, which effectively forces a specific language for users of the example. The policy requires flagging language or locale constraints when the skill does not offer user opt-in or justify the restriction.
SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructions and reference material exclusively in Chinese, with no opt-in, alternative language, or justification that the skill is region-specific.
No suspicious patterns detected.