SKILLEMALL.ai
GitHub ↗ RU Sign in

BC video-fetch-download

Download videos and torrents to cloud storage. Requires python3.12, rclone (115-fork, installed to ~/.local/bin), yt-dlp, and aria2c. Install via scripts/install.sh (installs all deps to user directory, no sudo; may append ~/.local/bin to PATH in shell profile). Writes credentials to ~/.config/rclone/rclone.conf (115 Pan, chmod 600) and ~/.config/video-fetch/quark_cookie.txt (Quark cookie, chmod 600) — stored locally only, never transmitted to third parties. Supports 115 offline download (server-side, zero local bandwidth), Quark Pan offline download and share link transfers, and 1000+ video site downloads via yt-dlp. Torrent search via Knaben API + apibay. Also supports Google Drive, OneDrive, Dropbox, and any rclone-compatible storage. Keywords: 离线下载, 下载视频, 磁力链, 种子, 夸克转存, 夸克离线, 115网盘, yt-dlp, 搜索电影, 磁力搜索.

ClawHub Agent Skills author: grayson v1.1.9 MIT-0 11 files · 2 scripts body ≈ 2 339 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationGoogle DriveMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
79/100
safety, quality, tests
Safety 60%
93
Quality 40%
58
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:190
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl https://rclone.org/install.sh | sudo bash
    vendor-host
  • low Secrets in code secret-password-literal scripts/quark_save.py:74
    Hard-coded password / key literal (may be an example) (detector / deny-list definition)
    match_pwd = re.search(r"pwd=([a-zA-Z0-9]+)", share_url)
    detector
  • low Dangerous commands cmd-privilege SKILL.md:190
    Privilege escalation / world-writable permissions (detector / deny-list definition)
    curl https://rclone.org/install.sh | sudo bash
    detector

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 3, column 14: description: Download videos and torrents to cloud storage. Requires python3.12… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 50/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 100Steps. 21 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2339 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 817: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 21 items
  • +4Has examples (17 code blocks)
  • +3All 8 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: suspicious
This skill mostly matches its cloud-download purpose, but its setup understates system-level changes and asks users to handle powerful cloud account credentials.
LLM: suspicious (high) · VirusTotal: · 29 May 2026