Security audit
Security checks for vulnerabilities and agentic risk
This skill fetches public Bilibili video metadata from Bilibili's API and asks the agent to summarize it, with no evidence of credential access, persistence, destructive behavior, or hidden unrelated actions.
Install only if you are comfortable with the BV video ID from your request being sent to Bilibili's public API. Expect metadata-based summaries rather than full transcript or video-content summaries, and note that the script filename typo may need correction for the skill to run reliably.
The declared behavior says the skill summarizes Bilibili videos, but the implementation reportedly only fetches structured/raw metadata and depends on external network access not disclosed in the description. This mismatch is dangerous because users and reviewers may approve the skill under false assumptions, while the hidden external-access behavior expands data flow and trust risks.
The skill invokes an internal script that performs network access, but the manifest does not declare any tool scope, permissions, or allowed-tools boundaries. This weakens reviewability and enforcement, making it easier for a skill to access external resources without transparent user or platform oversight.
The returned error messages and comments are in Chinese only, such as "未找到 BV 号" and "API 返回异常", with no indication that the user can choose another language. This can violate language/locale policy when a skill forces a specific language without user opt-in.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
// 2. 调 B站官方 API
const res = await fetch(
`https://api.bilibili.com/x/web-interface/view?bvid=${bvid}`,
{
headers: {
"User-Agent": "Mozilla/5.0"
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
// 2. 调 B站官方 API
const res = await fetch(
`https://api.bilibili.com/x/web-interface/view?bvid=${bvid}`,
{
headers: {
"User-Agent": "Mozilla/5.0"
This code performs an outbound HTTP request to Bilibili using a BV identifier extracted from the user's input, but there is no confirmation prompt, user-facing log, or inline disclosure indicating that part of the user's input will be sent to an external service. For code files, outbound transmission of user data should have some visible warning unless the disclosure is otherwise documented.
No suspicious patterns detected.