Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent Qixin enterprise-information lookup client with expected API-token and network use, though users should understand that company queries go to Qixin and fuzzy name matches may be imperfect.
Before installing, confirm you are allowed to send queried company names or IDs to Qixin, protect the QXBENT_API_TOKEN as a credential, and verify the returned ename when using fuzzy name lookup. For stronger supply-chain hygiene, prefer a reviewed lockfile or pinned dependency versions.
The skill declares runtime requirements and environment-variable access but does not clearly define an explicit tool scope or allowed-tools policy. This can lead to broader-than-expected execution capability, making it easier for an agent runtime to invoke code or access secrets without transparent user consent or tight policy enforcement.
The skill instructs users to query enterprise information through a third-party API but does not clearly warn that user-supplied company names or identifiers will be transmitted to an external service. This creates a privacy and data-governance risk, especially in due-diligence, procurement, or contract-review workflows where queried entities may reveal sensitive business intent.
The documentation states that when ename cannot be precisely matched, the system automatically uses the first search result, but it does not clearly warn users in the skill description or interface contract that this may return a different enterprise than intended. In a business due-diligence context, this can cause users or downstream agents to rely on incorrect corporate identity, status, or qualification data, leading to misverification of counterparties.
The description is written entirely in Chinese and presents the skill name and behavior only in that language. For a manifest file, this can be a natural-language locale policy issue if the skill is surfaced to general users without any opt-in, alternative locale, or documented region-specific constraint.
Using a caret range for axios allows future compatible releases to be installed without explicit review, which weakens supply-chain control. In this skill context, axios is a network-facing runtime dependency, so an unexpected vulnerable or malicious upstream release could affect request handling, SSRF exposure, or credential-bearing HTTP traffic.
"author": "",
"license": "MIT",
"dependencies": {
"axios": "^1.6.0"
},
"devDependencies": {
"@types/node": "^20.0.0",
The manifest uses axios without an exact pinned version, while the analyzer notes multiple known advisories affecting some axios releases. Because this skill appears to query external enterprise information over HTTP, a vulnerable axios version could expose network-layer risks such as SSRF bypasses, request manipulation, or interception-related issues depending on how the library is used elsewhere in the codebase.
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.
"axios": "^1.6.0"
},
"devDependencies": {
"@types/node": "^20.0.0",
"ts-node": "^10.9.0",
"typescript": "^5.0.0"
}
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.
},
"devDependencies": {
"@types/node": "^20.0.0",
"ts-node": "^10.9.0",
"typescript": "^5.0.0"
}
}
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.
"devDependencies": {
"@types/node": "^20.0.0",
"ts-node": "^10.9.0",
"typescript": "^5.0.0"
}
}
No suspicious patterns detected.