SKILLEMALL.ai

CF Downloader Tiktok Videos

Automatically downloads the latest video (or the N most recent) from a public TikTok account using yt-dlp. Use this skill whenever the user mentions TikTok, a @username, "download a TikTok video", "get the latest TikTok post", "scrape TikTok", or any request to download/extract content from TikTok. Also applies when the user wants to retrieve metadata only (title, hashtags, date, stats) without downloading, archive TikTok videos, or automate TikTok content retrieval.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: stx v1.0.4 5 files body ≈ 1 417 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 58/100 · Will not run — References files that are not bundled: references/metadata.md

ReferenceMarketingtype and topics are labelled automatically from the skill text
JSON
Technical rating
C
67/100
safety, quality, tests
Safety 60%
58
Quality 40%
81
Run on models
none yet
Process rating
F
58/100
Will not run
References files that are not bundled: references/metadata.md
Tools and files w 18
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The text references files that are not there: add them or drop the references.
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 · 4

  • high Exfiltration intent-browser-credential-store advanced.md:29
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser chrome URL
  • high Exfiltration intent-browser-credential-store advanced.md:35
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser edge URL
Medium and low: 2
  • medium Exfiltration intent-browser-credential-store SKILL.md:127
    Accesses a browser credential / cookie store (documentation table row)
    | `Private account` | Private account | Use `--cookies-from-browser chrome` if logged in ⚠️ exports session cookies — keep them private |
    table
  • low Exfiltration intent-browser-credential-store download_latest.py:216
    Accesses a browser credential / cookie store (test fixture / example file; quoted — discussed, not commanded)
    help="Export cookies from browser: chrome | firefox | edge (sensitive)"
    fixturequoted

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning missing-ref reference to a missing file: references/metadata.md

Process rating: all ten parameters 58/100

Will not run. References files that are not bundled: references/metadata.md
  • 0Tools and files. 1 referenced file(s) missing: references/metadata.md
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (Downloader Tiktok Videos) differs from the folder (downloader-tiktok-videos)
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 33 steps, 1 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 1417 tokens

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

  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 3 example trigger phrases
  • +3Description length 471: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 33 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

External checks

ClawHub: suspicious
This is a transparent TikTok downloader, but it reaches into browser-session cookies and host-level installs beyond a simple public-video download workflow.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026