DB video-download
Download videos from 1800+ websites and generate subtitles using Faster Whisper AI. Use when user wants to download videos from YouTube, Bilibili, Twitter, TikTok, Facebook, Vimeo, or any other supported video site, extract audio, or transcribe video content to text/subtitles.
Download videos from 1800+ websites and generate subtitles using Faster Whisper AI.
As a process B 72/100 · Nearly there — weak spots: when it triggers
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
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.
- 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
-
high Obfuscation
uni-zero-widthreferences/supportedsites.md:32Zero-width / invisible characters (possible hidden text) (37 occurrences)- **abc.net.au:␀iview:showseries**
-
high Exfiltration
intent-browser-credential-storeSKILL.md:191Accesses a browser credential / cookie store- Install the **Get cookies.txt LOCALLY** Chrome extension first.
Medium and low: 1
-
low Exfiltration
intent-browser-credential-storescripts/video_parser.py:583Accesses a browser credential / cookie store (security demo / example; quoted — discussed, not commanded)print('示例7 - 从浏览器读取 cookies: python video_parser.py \'{"urls":["URL"],"cookiesfrombrowser":"chrome"}\'')demoquoted
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 72/100
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 29 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1865 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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)
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 277: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 29 items
- +3Output format is stated explicitly
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.