Ae1
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 需要 Node.js 环境(已内置 `call-node.js`,无需额外依赖)
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent public financial-data API wrapper that sends user-selected market queries to ThemePica using an APPCODE credential, with no evidence of hidden execution, persistence, or destructive behavior.
Install only if you are comfortable using a ThemePica APPCODE and sending requested tickers, keywords, dates, and other query parameters to ThemePica's API. Prefer the THEMEPICA_APPCODE environment variable over storing a real key in mcp_config.json, and treat the finance outputs as data/analysis rather than automatic trading advice.
Referenced artifact was not completely inspected
需要 Node.js 环境(已内置 `call-node.js`,无需额外依赖)
Referenced artifact was not completely inspected
需要 Node.js 环境(已内置 `call-node.js`,无需额外依赖)
Without declared permissions the skill's intent is opaque and cannot be validated.
The manifest description and the entire user-facing documentation are presented in Chinese, and there is no indication that users can choose another language or that the skill is intentionally restricted to Chinese-speaking users. This can violate a language/locale policy when the skill is distributed to a broader audience without explicit opt-in.
This code accesses a credential-like value from process.env.THEMEPICA_APPCODE and later transmits requests, including user-supplied parameters, to an external API. While the file has technical comments, it does not provide a user-facing warning, confirmation, or disclosure about credential use and outbound data transmission.
makeRequest performs network requests and writes POST bodies derived from user input, and call also places GET parameters into the URL. The script lacks any explicit warning in code comments, docstrings, or user-facing output that request parameters will be sent to a third-party service.
This markdown file presents all user-facing descriptions, parameter explanations, and examples exclusively in Chinese. Under the policy, forcing a specific language without offering a choice or documenting a justified locale restriction is a natural-language policy violation.
This markdown file presents all user-facing descriptions, parameters, and examples exclusively in Chinese. Under the language/locale policy, forcing a specific language without user opt-in or documenting a justified regional constraint is a natural-language policy violation.
The only natural-language description in the file is written in Chinese ("验证所有25个公开API") with no indication that language choice is configurable or that the skill is intentionally region-specific. Per the policy, forcing a specific language without user opt-in is a natural-language locale violation.
The script executes shell commands via eval using a command string passed into run_test. Even though the current call sites are hardcoded, eval causes an additional round of shell parsing, so any future change that lets endpoint names, arguments, or command fragments come from untrusted input could lead to command injection. In this skill context, verify_all.sh is a test helper, which makes the immediate risk lower, but shelling out with eval is still an unsafe pattern in code that may be reused or modified.
Natural-language content in the file, including the header comments and inline documentation, is presented exclusively in Chinese. Under the language/locale policy, forcing a specific language without offering user choice or documenting a justified regional constraint is a policy concern.
The file presents the skill name, description, parameters, and return fields entirely in Chinese, with no indication that language choice is configurable or that the skill is intended only for a Chinese-speaking or region-specific audience. This can violate a language/locale policy when users are not given an explicit language option or explanation for the restriction.
This markdown file contains user-facing natural-language documentation only in Chinese, and it does not indicate that the skill is region-specific or that users may choose another language. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation.
This markdown file presents all user-facing documentation in a single language, which can violate language/locale policy when no user opt-in or justification is provided. The file does not indicate that the skill is intended only for Chinese-speaking users or a China-specific compliance context.
The document title and all interface descriptions are written entirely in Chinese, which effectively imposes a single language on users of the skill documentation. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative language option or justification is provided.
The script's comments and console output are written in Chinese throughout, including status banners and test messages, without any indication that language selection is configurable or intentionally region-specific. This can violate the language/locale policy for natural-language content because it forces a specific language without user opt-in.