Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed wrapper for a paid WeChat Channels replay-data API and does not show hidden persistence, deception, or unrelated local access.
Install only if you are comfortable using the Ман格云/api.we-media.cn service for WeChat Channels data, storing the API key locally, and paying per confirmed query. Keep page counts and output paths explicit, and do not paste API keys into chat or exported reports.
The stated function is specific to querying WeChat live replay resources, but the content mainly describes infrastructure-layer behaviors against a generic external API gateway and lacks clearly evidenced implementation of the core replay-list/detail logic. This is dangerous because it obscures the actual trust boundary and may cause data to be sent to a third-party platform under a misleading functional label.
The stated function is specific to querying WeChat live replay resources, but the content mainly describes infrastructure-layer behaviors against a generic external API gateway and lacks clearly evidenced implementation of the core replay-list/detail logic. This is dangerous because it obscures the actual trust boundary and may cause data to be sent to a third-party platform under a misleading functional label.
The stated function is specific to querying WeChat live replay resources, but the content mainly describes infrastructure-layer behaviors against a generic external API gateway and lacks clearly evidenced implementation of the core replay-list/detail logic. This is dangerous because it obscures the actual trust boundary and may cause data to be sent to a third-party platform under a misleading functional label.
The stated function is specific to querying WeChat live replay resources, but the content mainly describes infrastructure-layer behaviors against a generic external API gateway and lacks clearly evidenced implementation of the core replay-list/detail logic. This is dangerous because it obscures the actual trust boundary and may cause data to be sent to a third-party platform under a misleading functional label.
The skill declares capabilities that imply environment variable access, local file read/write, and outbound network use, but it does not define any explicit tool scope or permission boundaries. That creates an over-privileged execution model where a host agent may grant broader access than users expect, increasing the chance of unintended data exposure or unsafe file/network operations.
The skill description and operational instructions are entirely written in Chinese and present the workflow as fixed, with no indication that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
The skill explicitly directs outbound communication to a third-party domain and describes using API keys, product queries, and pricing endpoints. External transmission is expected for this skill, but it remains a real security concern because user-supplied query data and metadata about requests may be sent off-platform to an external service.
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。
This instruction continues to route execution toward third-party API documentation and product endpoints, confirming that the skill depends on external network transmission. In context, the risk is moderated by the explicit warning not to place API keys in chat, but outbound transfer of user queries and derived data still occurs and should be treated as sensitive.
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。
创建专属 Skill 不代表免除 API 调用费用，也不保证结果、收益或留存率。
The public product-directory endpoint is an external transmission path to a non-local service. Even if the endpoint itself is public, invoking it from within the skill establishes a network egress channel and may reveal usage patterns, user intent, or associated request metadata to the third-party operator.
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。
创建专属 Skill 不代表免除 API 调用费用，也不保证结果、收益或留存率。
The authenticated products endpoint implies transmitting requests tied to a user's API key and potentially account-specific pricing or product access data to an external service. Although the text advises against exposing the key in chat, the skill still performs sensitive third-party interactions that can affect privacy, billing, and auditability if not tightly scoped.
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。
创建专属 Skill 不代表免除 API 调用费用，也不保证结果、收益或留存率。
## 请求身份与安全
This code file contains natural-language instructions and operational messages exclusively in Chinese, and the same language choice continues throughout later print/error strings. That forces a specific language on users without opt-in, which matches the language/locale policy violation criteria.
This code contains natural-language documentation and multiple user-facing strings entirely in Chinese, establishing a de facto language requirement for using the skill. The policy only permits locale constraints when the skill offers a language choice or clearly justifies a region-specific limitation, which is not stated here.
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 shared core exposes generic endpoint listing and invocation scaffolding beyond the skill’s declared replay-only purpose, which increases the accessible attack surface and makes capability boundaries depend on external metadata rather than the skill manifest. In an agent setting, this can enable unintended data access or misuse if another wrapper script, prompt path, or user input reaches this generic core and invokes unrelated WeChat ecosystem endpoints.
The code raises user-visible ValueError messages in Chinese at L76 and L82. This is a natural-language locale constraint embedded in the skill without any opt-in, fallback, or documentation that the skill is intended only for Chinese-speaking users.
The manifest sets the user-facing display name entirely in Chinese ("视频号直播回放台") with no indication of optional localization or a documented region-specific constraint. This can violate language/locale policy when a skill imposes a single language without user opt-in.
This JSON manifest defines API endpoints and metadata but provides no information about what user phrases, contexts, or conditions should activate the associated skill. For manifest files, missing specificity on trigger scope can lead downstream systems or integrators to invoke the skill too broadly because there are no explicit activation boundaries or exclusion conditions.
The code raises a user-facing ValueError with a message written only in Chinese. This imposes a specific language on users without any opt-in or documented locale constraint, which matches the language/locale policy violation category.
The manifest describes a capability to list replay records and retrieve replay details and interaction data. This shared module also writes JSON, Markdown, and Excel files and generates polished reports on disk, which is not clearly part of the stated purpose and adds a broader local-output capability beyond simple retrieval.