Security audit
Security checks for vulnerabilities and agentic risk
This skill is a Chinese long-form fiction workflow that writes local story files and memory notes, with no evidence of hidden network access, credential use, or malicious behavior.
Install only if you want a Chinese serialized-novel workflow that writes markdown files locally. Use it in a dedicated project directory, review output/ and .learnings/ before reusing the workspace, and avoid --clean unless you are comfortable deleting prior generated chapter files and resetting story memory.
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 [ "$CLEAN" = true ]; then
log_step "清除旧的输出文件..."
rm -rf "$OUTPUT_DIR"/*.md 2>/dev/null || true
log_step "重置记忆文件..."
The initialization example includes ./scripts/init-novel.sh 我的小说名 --clean without explaining what --clean deletes or resets. A destructive flag presented as the default example can cause users or agents to remove prior outputs or state unintentionally, which is especially risky in automated environments where commands may be copied verbatim.
The skill description includes broad English activation phrases such as 'write a novel', 'generate fiction', and 'create stories', which can match many ordinary writing requests and cause the skill to be invoked when the user did not specifically ask for this workflow. Because the skill requires file read/write access and persistent memory behavior, over-triggering expands the chance of unintended filesystem modifications and inappropriate context capture.
The metadata specifies 'language: zh-CN', and the surrounding instructions are written as if the skill operates in Chinese by default. This can be a language/locale policy issue when the skill forces a specific language without an explicit opt-in, alternative language support, or a documented reason for the restriction.
The documentation instructs use of an initialization script that clears prior .learnings/ records, but it does not present a prominent warning, confirmation step, or backup guidance. In a skill with persistent memory and file write permissions, this creates a real risk of accidental data loss, including deletion of prior story state or other user-authored records stored in that workspace.
The file title and instructions are entirely in Chinese and direct the system to automatically expand user input into a completed prompt template, implying a fixed language/locale for the skill's output. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.
This markdown file presents all guidance exclusively in Chinese, starting from the title and continuing throughout the document. Under the policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.
The --clean path performs irreversible deletion of existing chapter outputs and overwrites all learning/memory files with template content without any confirmation, backup, or dry-run behavior. In an agent-integrated workflow, a mistaken flag, misunderstood user request, or automation bug can destroy accumulated novel state and prior work, causing significant integrity and availability loss.
The README presents the skill as a Chinese-language novel generator and the examples and instructions are all in Chinese, which may imply a fixed language/locale. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative or choice is documented.
The README states that each chapter is output as an independent markdown file and that memory files are automatically maintained, but it does not clearly warn users that using the skill will create and modify files in the workspace. In an agent-skill context, implicit file writes can surprise users, especially when run in repositories or shared workspaces, leading to unintended changes or polluted state.
The file's headings and instructional content are entirely in Chinese, including the title and all template sections, with no indication that language selection is optional. Under the policy for natural-language violations, a skill artifact that imposes a specific language without user opt-in can violate language or locale requirements.
This markdown guide is entirely written in Chinese and presents its instructions as the default behavior, with no indication that other languages are supported or that the user may choose their preferred language. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.
All user-facing comments, help text, status messages, and workflow instructions are presented only in Chinese. This imposes a fixed language choice on users without opt-in or an explicit statement that the skill is intentionally limited to a Chinese-language context.
No suspicious patterns detected.