SKILLEMALL.ai
GitHub ↗ RU Sign in

BD proxyclaw

ProxyClaw by IPLoop — Residential proxy access for AI agents. Route requests through 2M+ residential IPs across 195+ countries from real Android, Windows, Mac & Smart TV devices. Bypass geo-restrictions, rotate IPs automatically. Free tier with 0.5GB included. Earn unlimited proxy credits by contributing bandwidth via Docker. Use OPENCLAW for 20% off any paid plan.

ClawHub Agent Skills author: Ultronprime2026 v2.5.2 MIT-0 19 files · 2 scripts body ≈ 1 897 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureDockerInfrastructureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
78
Quality 40%
83
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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

    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 · 14

    ✓ No critical or high findings

    Medium and low: 14
    • medium Dangerous commands cmd-shell-rc rules/setup.md:20
      Writes to a shell startup file
      echo 'export IPLOOP_API_KEY="your_api_key"' >> ~/.bashrc
    • medium Exfiltration net-credential-use signup.html:345
      Credential used in a network call (verify the destination is the intended service)
      # curl -x "http://\${IPLOOP_CUSTOMER_ID}:\${IPLOOP_API_KEY}@\${IPLOOP_PROXY_URL}" https://httpbin.org/ip
    • low Exfiltration net-credential-use docs/SUPPORT-API.md:48
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://api.iploop.io/api/v1/usage -H "Authorization: Bearer $TOKEN"
      vendor-host
    • low Exfiltration net-credential-use docs/SUPPORT-API.md:59
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://api.iploop.io/api/v1/dashboard/summary -H "Authorization: Bearer $TOKEN"
      vendor-host
    • low Exfiltration net-credential-use docs/SUPPORT-API.md:73
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://api.iploop.io/api/v1/api-keys -H "Authorization: Bearer $TOKEN"
      vendor-host
    • low Exfiltration net-credential-use docs/SUPPORT-API.md:88
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://api.iploop.io/api/v1/proxy/config -H "Authorization: Bearer $TOKEN"
      vendor-host
    • low Exfiltration net-credential-use docs/SUPPORT-API.md:93
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://api.iploop.io/api/v1/nodes/countries -H "Authorization: Bearer $TOKEN"
      vendor-host
    • low Exfiltration net-credential-use earn/DOCKER.md:42
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://api.iploop.io/api/v1/earn/balance -H "Authorization: Bearer $TOKEN"
      vendor-host
    • low Exfiltration net-credential-use earn/DOCKER.md:45
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://api.iploop.io/api/v1/earn/devices -H "Authorization: Bearer $TOKEN"
      vendor-host
    • low Exfiltration net-credential-use SKILL.md:125
      Credential used in a network call (verify the destination is the intended service) (security demo / example; the skill's own vendor host)
      curl --proxy "http://prox…880" --proxy-user "iploop:${IPLOOP_API_KEY}-country-US" https://example.com
      demovendor-host
    • low Exfiltration net-credential-use SKILL.md:126
      Credential used in a network call (verify the destination is the intended service) (security demo / example; the skill's own vendor host)
      curl --proxy "http://prox…880" --proxy-user "iploop:${IPLOOP_API_KEY}-country-DE" https://example.com
      demovendor-host
    • low Exfiltration net-credential-use SKILL.md:127
      Credential used in a network call (verify the destination is the intended service) (security demo / example; the skill's own vendor host)
      curl --proxy "http://prox…880" --proxy-user "iploop:${IPLOOP_API_KEY}-country-GB" https://example.com
      demovendor-host
    • low Exfiltration net-credential-use SKILL.md:128
      Credential used in a network call (verify the destination is the intended service) (security demo / example; the skill's own vendor host)
      curl --proxy "http://prox…880" --proxy-user "iploop:${IPLOOP_API_KEY}-country-JP" https://example.com
      demovendor-host
    • low Exfiltration net-credential-use SKILL.md:129
      Credential used in a network call (verify the destination is the intended service) (security demo / example; the skill's own vendor host)
      curl --proxy "http://prox…880" --proxy-user "iploop:${IPLOOP_API_KEY}-country-BR" https://example.com
      demovendor-host

    Files scanned: 19. 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 49/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 2 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 14 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1897 tokens
    • low 11 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)
    • +3Output format is not stated: the model decides each time
    • -212 emoji in the instructions: noise for the model
    • -32 of 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 367: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 14 items
    • +4Has examples (13 code blocks)
    • +4Reference files are cited in the instructions (1 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: suspicious
    ProxyClaw is a real residential-proxy scraping skill, but it needs Review because it encourages broad proxy-routed scraping, anti-bot bypass, persistent bandwidth sharing, and account or payout actions without enough user consent and risk controls.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026