Security audit

bilibili-video-analysis

Security checks across malware telemetry and agentic risk

Overview

This skill coherently fetches public Bilibili video data for analysis, with optional local media and speech-recognition setup that is disclosed and user-gated.

Install only if you are comfortable with the skill sending video IDs, search terms, and related public-data requests to Bilibili and storing local caches. Optional visual/ASR features may install ffmpeg, Python packages, and ASR models after you approve the setup plan. Avoid providing Bilibili cookies unless you intentionally want authenticated requests; the reviewed flow does not automatically read browser cookies.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (50)

Credential Access

High

Category: Privilege Escalation
Content: # 本地环境变量 .env .env.local .env.*.local scripts/prototype/__pycache__/
Confidence: 60% confidence
Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High

Category: Privilege Escalation
Content: # 本地环境变量 .env .env.local .env.*.local scripts/prototype/__pycache__/ __pycache__/
Confidence: 60% confidence
Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Ae1

High

Category: analysis-evasion
Content: 先读取 [`references/task-routing.md`](references/task-routing.md)，内部形成：
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: 用户没有提供具体视频、而是给出主题或问题时，属于 `topic_research`：先按 [`references/discovery-strategy.md`](references/discovery-strategy.md) 发现候选，再对选中视频复用单视频流程。单视频任务不加载该策略。
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: 读取 [`references/data-routing.md`](references/data-routing.md) 中与当前 Intent / Focus 相关的部分，再规划：
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: - [`references/data-plan-schema.md`](references/data-plan-schema.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 视频搜索（仅 `topic_research` 阶段一） | [`references/tools/video-search.md`](references/tools/video-search.md) |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 当前热门快照（平台热门机制，非排行榜） | [`references/tools/popular-videos.md`](references/tools/popular-videos.md) |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 当前热搜词条（搜索关注度快照，非事件背景） | [`references/tools/hot-searches.md`](references/tools/hot-searches.md) |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 给定视频的关联推荐（推荐邻接关系，非主题等价） | [`references/tools/related-videos.md`](references/tools/related-videos.md) |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 视频元信息 | [`references/tools/metadata.md`](references/tools/metadata.md) |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | Transcript（官方字幕 + ASR fallback） | [`references/tools/subtitle.md`](references/tools/subtitle.md) |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 弹幕 | [`references/tools/danmaku.md`](references/tools/danmaku.md) |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 评论 / 回复 | [`references/tools/comments.md`](references/tools/comments.md) |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 关键帧 / 视觉变化候选 | [`references/tools/frames.md`](references/tools/frames.md) |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: - `content_learn` → [`references/analysis/content-learn.md`](references/analysis/content-learn.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: - `visual_decode` → [`references/analysis/visual-decode.md`](references/analysis/visual-decode.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: - `visual_decode` → [`references/analysis/visual-decode.md`](references/analysis/visual-decode.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: - `audience_insight` → [`references/analysis/audience-insight.md`](references/analysis/audience-insight.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: - `market_research` → [`references/analysis/market-research.md`](references/analysis/market-research.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: - `market_research` → [`references/analysis/market-research.md`](references/analysis/market-research.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: - `topic_research` → [`references/analysis/topic-research.md`](references/analysis/topic-research.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Lp3

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

External Transmission

Medium

Category: Data Exfiltration
Content: audio-download: B 站 audio.m4s 下载 (Web API 自实现, 不依赖 yt-dlp) B 站 audio.m4s 直链获取有两种方式: A) 旧 API: https://api.bilibili.com/x/player/playurl?bvid=X&cid=Y&qn=16 - 优点: 不用 WBI 签名, 只要 SESSDATA - 缺点: 2024+ 部分视频要求 fnval=16/4048 强制 DASH B) 新 API: https://api.bilibili.com/x/player/wbi/playurl?bvid=X&cid=Y
Confidence: 60% confidence
Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

Category: Data Exfiltration
Content: audio-download: B 站 audio.m4s 下载 (Web API 自实现, 不依赖 yt-dlp) B 站 audio.m4s 直链获取有两种方式: A) 旧 API: https://api.bilibili.com/x/player/playurl?bvid=X&cid=Y&qn=16 - 优点: 不用 WBI 签名, 只要 SESSDATA - 缺点: 2024+ 部分视频要求 fnval=16/4048 强制 DASH B) 新 API: https://api.bilibili.com/x/player/wbi/playurl?bvid=X&cid=Y
Confidence: 60% confidence
Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.dynamic_code_execution

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/build-release.mjs:35

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/cli/commands/setup.ts:276

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/subtitle/asr/runner.ts:176

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/verify-release.mjs:9

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/visual/frame-extractor.ts:379

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/visual/media-probe.ts:175

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/visual/scene-detector.ts:108

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: tests/unit/run-tool.test.ts:21

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: tests/python/test_audio_download.py:18

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: tests/python/test_pipeline_contract.py:11