DB video-downloader-enhanced
Download videos and extract original post captions, audio transcripts, and metadata from video platform links. Use when the user provides Douyin, Bilibili, WeChat Channels, Xiaohongshu, or YouTube links and asks to save the original video, capture the post text/caption, transcribe the spoken in-video script/copy, archive source material, or prepare video material for downstream analysis or skill creation. Douyin is implemented with an H5 primary route and yt-dlp fallback; Bilibili, YouTube, and Xiaohongshu are implemented through yt-dlp; WeChat Channels is not implemented yet and should currently be handled via the WeChat mini program kg百宝箱.
Download videos and extract original post captions, audio transcripts, and metadata from video platform links.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions
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.
- 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 · 7
-
high Exfiltration
intent-browser-credential-storeREADME.md:206Accesses a browser credential / cookie storeyt-dlp --cookies-from-browser chrome
-
high Exfiltration
intent-browser-credential-storeSKILL.md:217Accesses a browser credential / cookie store3. **Chrome cookies yt-dlp** — last resort; requires local Chrome browser access.
Medium and low: 5
-
medium Exfiltration
intent-browser-credential-storescripts/providers/bilibili.py:79Accesses a browser credential / cookie store (quoted — discussed, not commanded)[yt_dlp, "--cookies-from-browser", "chrome", "--no-playlist", "--dump-single-json", url],
quoted -
medium Exfiltration
intent-browser-credential-storescripts/providers/douyin.py:263Accesses a browser credential / cookie store (quoted — discussed, not commanded)[yt_dlp, "--cookies-from-browser", "chrome", "--no-playlist", "--dump-single-json", url],
quoted -
medium Exfiltration
intent-browser-credential-storescripts/providers/xiaohongshu.py:465Accesses a browser credential / cookie store (quoted — discussed, not commanded)"--cookies-from-browser", "chrome",
quoted -
medium Exfiltration
intent-browser-credential-storescripts/providers/youtube.py:80Accesses a browser credential / cookie store (quoted — discussed, not commanded)+ ["--cookies-from-browser", "chrome", "--dump-single-json", url],
quoted -
medium Exfiltration
intent-browser-credential-storescripts/providers/youtube.py:120Accesses a browser credential / cookie store (quoted — discussed, not commanded)command.extend(["--cookies-from-browser", "chrome"])
quoted
Files scanned: 11. 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 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 85 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 2874 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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)
- -32 of 3 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 649: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 85 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.