FB suiwarp
Deploy S-UI + Cloudflare WARP proxy server in one command. 6 protocols (VLESS Reality, TUIC, Hysteria2, gRPC, Trojan, WebSocket), clean Cloudflare IP exit via wireproxy (~54MB RAM). Use when the user wants to set up a proxy server, VPN alternative, or network tunnel on a VPS.
As a process B 74/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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 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.
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.
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 · 13
-
high Dangerous commands
cmd-pipe-to-shellREADME.md:6Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -sL https://raw.githubusercontent.com/iPythoning/SUIWARP/main/setup.sh)
-
high Dangerous commands
cmd-pipe-to-shellREADME.md:64Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -sL https://raw.githubusercontent.com/iPythoning/SUIWARP/main/setup.sh)
-
high Dangerous commands
cmd-pipe-to-shellREADME.md:166Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -sL https://raw.githubusercontent.com/iPythoning/SUIWARP/main/uninstall.sh)
-
high Dangerous commands
cmd-pipe-to-shellsetup.sh:83Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -sL "$S_UI_INSTALL_URL") <<< "y" || { -
high Dangerous commands
cmd-pipe-to-shellsetup.sh:85Downloads and executes remote code from an unrecognised host (pipe to shell)echo "y" | bash <(curl -sL "$S_UI_INSTALL_URL")
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:46Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -sL https://raw.githubusercontent.com/iPythoning/SUIWARP/main/setup.sh)
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:141Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -sL https://raw.githubusercontent.com/iPythoning/SUIWARP/main/uninstall.sh)
Medium and low: 6
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:64Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)ssh root@SERVER_IP 'bash <(curl -sL https://raw.githubusercontent.com/iPythoning/SUIWARP/main/setup.sh)'
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:70Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)'bash <(curl -sL https://raw.githubusercontent.com/iPythoning/SUIWARP/main/setup.sh)'
quoted -
low Dangerous commands
cmd-background-processsetup.sh:87Starts a background / autostarted processsystemctl enable s-ui
-
low Dangerous commands
cmd-background-processsetup.sh:434Starts a background / autostarted processsystemctl enable wireproxy-warp
-
low Dangerous commands
cmd-background-processsetup.sh:617Starts a background / autostarted processsystemctl enable suiwarp-shadowtls
-
low Secrets in code
secret-password-literalsetup.sh:791Hard-coded password / key literal (may be an example) (placeholder value)info "Change panel password: http://${SERVER_IP}:2095/app/"placeholder
Files scanned: 5. 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 74/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1181 tokens
- low 10 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
- +2Single-language instructions
- +3Description length 276: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (11 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.