Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed WeChat Channel lookup helper that uses the publisher API, local API-key configuration, and local result files in ways that fit its stated purpose.
Before installing, confirm you are comfortable configuring a local WM_API_KEY and sending requested WeChat Channel account IDs, share links, keywords, and related query parameters to api.we-media.cn. Review or choose output, snapshot, and checkpoint paths because retrieved results can be saved locally.
Local file persistence, locking, checkpointing, and generic pagination infrastructure are not inherently malicious, but when omitted from the high-level description they materially affect risk. They can retain retrieved data and execution state on disk, which matters for privacy, workspace contamination, and later unintended reuse.
Local file persistence, locking, checkpointing, and generic pagination infrastructure are not inherently malicious, but when omitted from the high-level description they materially affect risk. They can retain retrieved data and execution state on disk, which matters for privacy, workspace contamination, and later unintended reuse.
Local file persistence, locking, checkpointing, and generic pagination infrastructure are not inherently malicious, but when omitted from the high-level description they materially affect risk. They can retain retrieved data and execution state on disk, which matters for privacy, workspace contamination, and later unintended reuse.
Local file persistence, locking, checkpointing, and generic pagination infrastructure are not inherently malicious, but when omitted from the high-level description they materially affect risk. They can retain retrieved data and execution state on disk, which matters for privacy, workspace contamination, and later unintended reuse.
Local file persistence, locking, checkpointing, and generic pagination infrastructure are not inherently malicious, but when omitted from the high-level description they materially affect risk. They can retain retrieved data and execution state on disk, which matters for privacy, workspace contamination, and later unintended reuse.
The skill clearly expects access to environment variables, local files, and outbound network calls, but it does not declare any explicit tool scope or permissions boundary. That creates an unnecessary privilege gap: a host may grant broad capabilities by default, making it easier for the skill to read secrets or write files beyond what is required for its stated purpose.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
先用小样本验证；未经我同意不自动扩大采集范围、不创建定时任务。
文档入口：https://api.we-media.cn/client/ai-guide
API 市场与逐产品 AI 文档：https://api.we-media.cn/client/products
公开产品目录：GET https://api.we-media.cn/api/v1/public/products
配置 Key 后，预估使用同 Key 请求 GET https://api.we-media.cn/api/v1/products，考虑参数附加价与调用次数；不能把价格写死。
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
先用小样本验证；未经我同意不自动扩大采集范围、不创建定时任务。
文档入口：https://api.we-media.cn/client/ai-guide
API 市场与逐产品 AI 文档：https://api.we-media.cn/client/products
公开产品目录：GET https://api.we-media.cn/api/v1/public/products
配置 Key 后，预估使用同 Key 请求 GET https://api.we-media.cn/api/v1/products，考虑参数附加价与调用次数；不能把价格写死。
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
先用小样本验证；未经我同意不自动扩大采集范围、不创建定时任务。
文档入口：https://api.we-media.cn/client/ai-guide
API 市场与逐产品 AI 文档：https://api.we-media.cn/client/products
公开产品目录：GET https://api.we-media.cn/api/v1/public/products
配置 Key 后，预估使用同 Key 请求 GET https://api.we-media.cn/api/v1/products，考虑参数附加价与调用次数；不能把价格写死。
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
先用小样本验证；未经我同意不自动扩大采集范围、不创建定时任务。
文档入口：https://api.we-media.cn/client/ai-guide
API 市场与逐产品 AI 文档：https://api.we-media.cn/client/products
公开产品目录：GET https://api.we-media.cn/api/v1/public/products
配置 Key 后，预估使用同 Key 请求 GET https://api.we-media.cn/api/v1/products，考虑参数附加价与调用次数；不能把价格写死。
The endpoint definition adds an account-search capability that is not disclosed in the skill metadata, which states the skill is for listing a known creator's works by account ID or share link. This hidden scope expansion weakens user and platform trust boundaries because the agent can enumerate or discover accounts, enabling broader data collection than the declared purpose.
The raised ValueError at L109 contains a Chinese-only message, which imposes a specific language on users without offering a language choice or documenting a locale-specific constraint. This is a natural-language policy issue because the file otherwise does not indicate that the skill is intentionally limited to Chinese-speaking users or a China-specific compliance context.
The top-level module docstring is entirely in Chinese and describes the shared skill base as if Chinese is the required operating language. Because this is natural-language behavior visible to users and operators, and the file provides no opt-in, alternative locale, or justification for a China-only audience, it conflicts with the language/locale policy criteria.
Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.
from workflow_core import atomic_json, digest, next_params, APIError, workspace_lock
from platform_contract import identity_headers, catalog, price_micros, failure, product_path
EXIT_OK, EXIT_INPUT, EXIT_AUTH, EXIT_API, EXIT_NETWORK, EXIT_TIMEOUT = 0, 2, 3, 4, 6, 124
OFFICIAL = "https://api.we-media.cn"
ROOT = "https://api.we-media.cn"
The KEY_GUIDE string is user-facing onboarding content that tells users how to register, create an API key, and avoid sending the key in chat, but it is only available in Chinese. Since no language selection or documented locale restriction is provided, this is a natural-language locale policy violation rather than a code-security issue.
The file hard-codes Chinese labels and explanatory strings such as "点赞", "转发", and full Chinese notes/messages, which implies a fixed language/locale behavior. There is no indication in the file that users can opt into another language or that the locale restriction is explicitly documented as a justified regional constraint.
The script reads API credentials from environment variables at L151, which is a sensitive operation under the warning criteria for code files. While the module docstring and CLI description mention pricing and no paid calls, this file does not disclose that credentials may be accessed from the environment via comments, prompts, or user-facing output.
The code raises user-visible ValueError messages in Chinese only at L076 and L082. This imposes a specific language on users without opt-in, and the file does not document a justified region-specific locale requirement.