DD supurr
Backtest, deploy, and monitor trading bots on Hyperliquid. Supports Grid, DCA, and Spot-Perp Arbitrage strategies across Native Perps, Spot markets (USDC/USDH), and HIP-3 sub-DEXes.
Backtest, deploy, and monitor trading bots on Hyperliquid.
As a process D 36/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 Dangerous commands
cmd-pipe-to-shellREADME.md:19Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://cli.supurr.app/skill-install | bash
vendor-host -
medium Dangerous commands
cmd-pipe-to-shellREADME.md:27Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://cli.supurr.app/install | bash
vendor-host -
medium Dangerous commands
cmd-pipe-to-shellREADME.md:40Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://cli.supurr.app/install | bash
vendor-host -
medium Dangerous commands
cmd-shell-rcscripts/install.sh:219Writes to a shell startup fileecho -e " ${YELLOW}⚠${NC} Open a new terminal or run: ${CYAN}source ~/.zshrc${NC}" -
medium Dangerous commands
cmd-pipe-to-shellscripts/skill-install.sh:159Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://cli.supurr.app/install | bash
vendor-host -
medium Risky intent
intent-wallet-secretsSKILL.md:60Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target| `--api-wallet <key>` | API wallet private key |
-
medium Risky intent
intent-wallet-secretsSKILL.md:433Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetSigns `Stop <bot-id>` with your API wallet private key (EIP-191 personal_sign) and sends the signature to the bot API.
-
low Dangerous commands
cmd-pipe-to-shellscripts/install.sh:4Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment; the skill's own vendor host)# Usage: curl -fsSL https://cli.supurr.app/install | bash
commentvendor-host -
low Dangerous commands
cmd-pipe-to-shellscripts/skill-install.sh:4Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment; the skill's own vendor host)# Usage: curl -fsSL https://cli.supurr.app/skill-install | bash
commentvendor-host -
low Dangerous commands
cmd-pipe-to-shellscripts/skill-install.sh:167Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)info "Re-run anytime to update: ${CYAN}curl -fsSL https://cli.supurr.app/skill-install | bash${NC}"code literalvendor-host
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6633 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 36/100
- 0Result and completion. Does not say what the result is
- 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. 15 mutating operations with no state check
- 40Consistency. Frontmatter name (supurr) differs from the folder (supurr-hyperliquid)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Steps. 13 steps, 4 vague phrases
- 70Execution cost. Instruction body is 6633 tokens
- low 24 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (32 tags): a typed call is more reliable
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 181: enough signal without eating the budget
- +4Structure: 51 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (27 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.