CC scrapling-official
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; web_fetch fails; the site has anti-bot protections; write Python code to scrape/crawl; or write spiders.
As a process C 60/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Exfiltration
exfil-webhook-urlreferences/fetching/static.md:53Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)page = Fetcher.get('https://scrapling.requestcatcher.com/get', stealthy_headers=True)quoted -
medium Exfiltration
exfil-webhook-urlreferences/fetching/static.md:54Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)page = Fetcher.get('https://scrapling.requestcatcher.com/get', proxy='http://username:password@loca…030')quoted -
medium Exfiltration
exfil-webhook-urlreferences/fetching/static.md:72Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)page = await AsyncFetcher.get('https://scrapling.requestcatcher.com/get', stealthy_headers=True)quoted -
medium Exfiltration
exfil-webhook-urlreferences/fetching/static.md:73Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)page = await AsyncFetcher.get('https://scrapling.requestcatcher.com/get', proxy='http://username:password@loca…030')quoted -
medium Exfiltration
exfil-webhook-urlreferences/fetching/static.md:107Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)page = Fetcher.post('https://scrapling.requestcatcher.com/post', data={'key': 'value'}, params={'q': 'query'})quoted -
medium Exfiltration
exfil-webhook-urlSKILL.md:133Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)scrapling extract get "https://scrapling.requestcatcher.com" content.md --cookies "session=abc123; user=john"
quoted -
medium Exfiltration
exfil-webhook-urlSKILL.md:184Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)scrapling extract fetch "https://scrapling.requestcatcher.com/" content.md --network-idle
quoted -
medium Exfiltration
exfil-webhook-urlSKILL.md:187Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)scrapling extract fetch "https://scrapling.requestcatcher.com/" data.txt --wait-selector ".content-loaded"
quoted -
medium Exfiltration
exfil-webhook-urlSKILL.md:190Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)scrapling extract fetch "https://scrapling.requestcatcher.com/" page.html --no-headless --disable-resources
quoted -
medium Exfiltration
exfil-webhook-urlSKILL.md:193Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)scrapling extract stealthy-fetch "https://scrapling.requestcatcher.com" content.md
quoted
Files scanned: 27. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6043 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6043 tokens
- 100Steps. 25 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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)
- +2Single-language instructions
- +3Description length 342: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 25 items
- +3Output format is stated explicitly
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.