Security audit
Security checks for vulnerabilities and agentic risk
This skill appears to optimize 1688 product titles, but it should be reviewed because it uses a merchant access key and defaults to operating across every bound shop when a shop is not specified.
Install only if you expect this skill to use a 1688 merchant access key, contact gateway.1688.com, retrieve bound-shop metadata, and run title optimization across every bound shop unless you explicitly specify one. Prefer scoping each request to a named shop/loginId, review telemetry expectations, and confirm carefully before allowing any external one-click title update.
Returning store/account binding information and loginId lists is broader than the declared title-rewrite purpose. Even if used operationally, exposing such metadata without clear disclosure can leak organizational structure and facilitate unintended cross-tenant access patterns.
Returning store/account binding information and loginId lists is broader than the declared title-rewrite purpose. Even if used operationally, exposing such metadata without clear disclosure can leak organizational structure and facilitate unintended cross-tenant access patterns.
Returning store/account binding information and loginId lists is broader than the declared title-rewrite purpose. Even if used operationally, exposing such metadata without clear disclosure can leak organizational structure and facilitate unintended cross-tenant access patterns.
Returning store/account binding information and loginId lists is broader than the declared title-rewrite purpose. Even if used operationally, exposing such metadata without clear disclosure can leak organizational structure and facilitate unintended cross-tenant access patterns.
Returning store/account binding information and loginId lists is broader than the declared title-rewrite purpose. Even if used operationally, exposing such metadata without clear disclosure can leak organizational structure and facilitate unintended cross-tenant access patterns.
Returning store/account binding information and loginId lists is broader than the declared title-rewrite purpose. Even if used operationally, exposing such metadata without clear disclosure can leak organizational structure and facilitate unintended cross-tenant access patterns.
Returning store/account binding information and loginId lists is broader than the declared title-rewrite purpose. Even if used operationally, exposing such metadata without clear disclosure can leak organizational structure and facilitate unintended cross-tenant access patterns.
Returning store/account binding information and loginId lists is broader than the declared title-rewrite purpose. Even if used operationally, exposing such metadata without clear disclosure can leak organizational structure and facilitate unintended cross-tenant access patterns.
Returning store/account binding information and loginId lists is broader than the declared title-rewrite purpose. Even if used operationally, exposing such metadata without clear disclosure can leak organizational structure and facilitate unintended cross-tenant access patterns.
The examples explicitly describe side-effecting actions such as writing selected data directly to a database, creating purchase orders, re-running searches with changed criteria, and blacklisting items. These operations are far outside the justified context of title optimization and could cause unauthorized business changes if an agent treats these examples as available patterns to emulate.
The documentation describes immediate order creation using a default shipping address and placing the order into a payment workflow without an explicit safety warning or confirmation step. This is a high-risk transactional side effect that is completely unrelated to title optimization and could produce financial loss, operational disruption, or accidental procurement if followed by an agent.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
职责：每次 CLI 命令执行时，向 skill 网关上报一次调用记录，用于统计 skill 调用次数。
上报失败不影响主流程，静默处理。
环境变量（从项目根目录 .env 读取）：
SKILL_NAME skill 名称，默认 1688-item-title-optimizer
SKILL_VERSION skill 版本，默认 1.0.0
SKILL_CHANNEL 发布渠道，默认 clawhubai
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
职责：每次 CLI 命令执行时，向 skill 网关上报一次调用记录，用于统计 skill 调用次数。
上报失败不影响主流程，静默处理。
环境变量（从项目根目录 .env 读取）：
SKILL_NAME skill 名称，默认 1688-item-title-optimizer
SKILL_VERSION skill 版本，默认 1.0.0
SKILL_CHANNEL 发布渠道，默认 clawhubai
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
职责：每次 CLI 命令执行时，向 skill 网关上报一次调用记录，用于统计 skill 调用次数。
上报失败不影响主流程，静默处理。
环境变量（从项目根目录 .env 读取）：
SKILL_NAME skill 名称，默认 1688-item-title-optimizer
SKILL_VERSION skill 版本，默认 1.0.0
SKILL_CHANNEL 发布渠道，默认 clawhubai
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
def _load_env_file() -> None:
"""解析项目根目录的 .env 文件，将变量注入 os.environ（已有环境变量不覆盖）。"""
env_path = _ROOT_DIR / ".env"
if not env_path.exists():
return
with open(env_path, encoding="utf-8") as f:
The file implements a CLI for configuring and validating an access key, which is outside the declared purpose of a title-optimization skill. In an agent-skill context, unexpected credential-management functionality materially increases risk because it can be used to solicit, process, or retain sensitive secrets without clear user expectation or business justification.
The skill declares no explicit tool scope or permission boundaries even though it uses environment variables, file reads, and network access. This weakens platform enforcement and reviewer visibility, making it easier for the skill to access credentials and external endpoints beyond what a user would infer from a title-optimization tool.
Overly broad trigger phrases increase the chance the skill activates on ambiguous everyday language. In this skill's context, accidental activation is more dangerous because it can lead to shop enumeration, credential-dependent API use, and exposure of merchant data beyond the user's intent.
The skill mandates enumerating all bound shops and operating across them by default when the user does not specify a shop. That creates an unsafe default that can unnecessarily process and surface data from unrelated shops, violating least surprise and increasing cross-tenant exposure risk.
The document does not prominently warn users that the default behavior is to traverse all bound shops. Missing disclosure undermines informed consent and makes accidental bulk cross-shop processing more likely in a sensitive merchant-management context.
Default cross-store enumeration and execution can expose titles, item IDs, and other shop-linked metadata in aggregated results from stores the user did not explicitly choose. In a multi-tenant commerce environment, that context makes the issue materially more dangerous because it breaks expected data scoping boundaries.
This markdown file presents all user-facing instructions, parameters, errors, and display requirements only in Chinese. The policy calls for flagging language or locale constraints when a specific language is forced without user opt-in, and no alternative language option or justification is provided here.
The manifest frames the skill as focused on optimizing 1688 product titles, but the CLI documentation and command discovery expose additional commands such as configure, get_keyword_info, and get_tokenizers. Those capabilities go beyond the stated optimization-focused behavior and indicate the skill does more than the manifest description claims.
The code scans capabilities/*/cmd.py and registers every discovered command at runtime, rather than limiting execution to known title-optimization functions. This makes the effective behavior of the skill broader than the manifest's described purpose, because any additional capability module placed in that directory becomes part of the exposed skill surface.
The CLI reports telemetry after every command execution via report_skill_usage() without any visible notice, consent flow, or opt-out in this file. Silent telemetry can expose usage patterns and potentially sensitive operational metadata, which is more concerning in a skill handling user-provided product titles and optimization requests.
No suspicious patterns detected.