Security audit
Security checks for vulnerabilities and agentic risk
This skill coherently fetches public Bilibili ranking data and saves it locally, with no evidence of hidden credential use, exfiltration, persistence, or destructive behavior.
Install this only if you are comfortable with it contacting Bilibili's API when invoked and creating or overwriting workspace/scripts/bilibili-hot.json and workspace/scripts/bilibili-hot.txt with public ranking results. It does not appear to request credentials or modify system settings.
The skill declares no explicit tool scope or permission boundary even though the analyzer detected environment-related capabilities. In an agent ecosystem, missing scope declarations can lead to overbroad execution context and make it harder for users or orchestrators to enforce least privilege.
The skill states that it will save results to local files but does not warn the user that files will be created or potentially overwritten. Silent filesystem writes are risky in agent settings because they can alter workspace state unexpectedly, destroy existing data, or leave sensitive output behind without user awareness.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
const OUTPUT_DIR = path.join(WORKSPACE, 'scripts');
// B站全站排行榜API
const BILI_RANK_API = 'https://api.bilibili.com/x/web-interface/ranking/v2?rid=0&type=all';
async function fetchBilibiliRank() {
return new Promise((resolve, reject) => {
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
const OUTPUT_DIR = path.join(WORKSPACE, 'scripts');
// B站全站排行榜API
const BILI_RANK_API = 'https://api.bilibili.com/x/web-interface/ranking/v2?rid=0&type=all';
async function fetchBilibiliRank() {
return new Promise((resolve, reject) => {
The skill description says it fetches Bilibili ranking data, but the code also writes that data into workspace files as JSON and text. This is a real behavior mismatch that can surprise a caller or downstream agent, because filesystem persistence creates side effects beyond simple retrieval and may expose fetched content to other tools or later steps.
The skill documents that it contacts a remote API but does not provide a user-facing network/privacy warning. Even if the API is official and public, outbound requests can disclose usage patterns, IP information, headers, and timing metadata to the remote service.
No suspicious patterns detected.