Waxell

skill

bilibili-source High risk

daymadedaymade/claude-code-skillsupdated

Fetches real, citable Bilibili (B站) video data, stats, metadata, tags, and full danmaku text, via login-free API calls, never hand-typed or estimated. Use when citing view/like/favorite counts, analyzing why a video performed, or archiving a Bilibili source into a knowledge base. Accepts BVID, av numbers, b23.tv links, or full URLs; subtitles and 收藏夹 (favorites) enumeration need the user's Bilibili login.
daymade's own description, from the skill's files.
Stars
1,534
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 29 findings, highest severity high.

Highest severity
high
Findings
29
What ran
Static analysis + deep scan

A clean result means nothing alarming in what is published, not a guarantee. How the checks work

We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.

Security

Security scan

Checked yesterday

Result

High risk Waxell rates it high risk: 29 findings, highest severity high.

Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work

Findings (29)

high · 9

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:18 · skillspector:AE1

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:42 · skillspector:AE1

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:48 · skillspector:AE1

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:54 · skillspector:AE1

  • high

    Supply Chain: External Script Fetching

    references/bilibili_api.md:83 · skillspector:SC2

  • high

    YARA Match: YARA rule 'info_stealer': Information stealer patterns (credential harvesting, browser data theft) [malware]

    references/bilibili_api.md:99 · skillspector:YR1

  • high

    Supply Chain: External Script Fetching

    scripts/bili-danmaku.sh:40 · skillspector:SC2

  • high

    Rogue Agent: Self-Modification

    scripts/bili-selftest.sh:63 · skillspector:RA1

  • high

    Tells Claude to install unpinned packages (yt-dlp)

    scripts/bili-subs.sh:23 · skill_risk:S2

medium · 18

  • medium

    Without declared permissions the skill's intent is opaque and cannot be validated.

    SKILL.md:1 · skillspector:LP3

  • medium

    Dangerous Code Execution: subprocess module call

    scripts/_audio_object.py:22 · skillspector:AST4

  • medium

    Data Exfiltration: External Transmission

    references/bilibili_api.md:42 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    references/bilibili_api.md:47 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    references/bilibili_api.md:83 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    references/bilibili_api.md:107 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    references/bilibili_api.md:131 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    references/bilibili_api.md:136 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    references/bilibili_api.md:141 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    scripts/bili-access.py:355 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    scripts/bili-danmaku.sh:40 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    scripts/bili-fetch.sh:57 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    scripts/bili-selftest.sh:65 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    scripts/bili-selftest.sh:80 · skillspector:E1

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_access.py:203 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_access.py:208 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_access.py:210 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_access.py:212 · skillspector:AST4

low · 2

  • low

    Dangerous Code Execution: Dynamic attribute access via getattr()

    scripts/bili-access.py:422 · skillspector:AST7

  • low

    Dangerous Code Execution: Dynamic attribute access via getattr()

    scripts/bili-access.py:422 · skillspector:AST7

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

  1. v22026-11-162 added, 2 changed High riskgot riskier
  2. v12026-11-03 Review findings

Files

Files

11 files, 92 KB in total. Names only; open them on GitHub.

  • SKILL.md
  • evals/evals.json
  • references/bilibili_api.md
  • scripts/_audio_object.py
  • scripts/bili-access.py
  • scripts/bili-danmaku.sh
  • scripts/bili-fetch.sh
  • scripts/bili-selftest.sh
  • scripts/bili-subs.sh
  • tests/test_access.py
  • tests/test_audio_object.py

See and control which skills your people use

Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.

30 minutes. No commitment.

SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF

More engineering skills and plugins

See all