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.
As a process F 58/100 · Will not run — References files that are not bundled: references/metadata.md
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.
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".
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
- 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.
- The text references files that are not there: add them or drop the references.
- 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-storeadvanced.md:29Accesses a browser credential / cookie storeyt-dlp --cookies-from-browser chrome URL
-
high Exfiltration
intent-browser-credential-storeadvanced.md:35Accesses a browser credential / cookie storeyt-dlp --cookies-from-browser edge URL
Medium and low: 2
-
medium Exfiltration
intent-browser-credential-storeSKILL.md:127Accesses 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-storedownload_latest.py:216Accesses 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-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
missing-refreference to a missing file: references/metadata.md
Process rating: all ten parameters 58/100
- 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.