DF Decision Economic Optimizer
Deterministic decision-ranking API with HTTP 402 USDC payments and outcome credits (discounts).
Deterministic decision-ranking API with HTTP 402 USDC payments and outcome credits (discounts).
As a process F 38/100 · Will not run — References files that are not bundled: "https://api.which-llm.com/report/wrong_address"
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.
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
- 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.
- 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.
- The text references files that are not there: add them or drop the references.
- 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 Dangerous commands
cmd-pipe-to-shellSKILL.md:314Downloads and executes remote code from an unrecognised host (pipe to shell)curl -L https://foundry.paradigm.xyz | bash
Medium and low: 6
-
medium Risky intent
intent-wallet-secretsSKILL.md:84Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target#### Option 2: Mnemonic Phrase
-
medium Risky intent
intent-wallet-secretsSKILL.md:86Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target**Format:** 12 or 24-word BIP-39 seed phrase
-
medium Risky intent
intent-wallet-secretsSKILL.md:102Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target#### Option 3: Keystore File + Password
-
medium Risky intent
intent-wallet-secretsSKILL.md:104Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target**Format:** Encrypted JSON keystore file (Ethereum standard) + password
-
medium Risky intent
intent-wallet-secretsSKILL.md:116Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- ⚠️ **File management overhead** - Must securely store keystore file
-
low Risky intent
intent-wallet-secretsskill.json:53Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)"format": "12 or 24-word BIP-39 seed phrase",
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 8220 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: "https://api.which-llm.com/report/wrong_address" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "credentials_required" - note
frontmatter-keyunknown frontmatter key "primary_credential"
Process rating: all ten parameters 38/100
- 0Tools and files. 1 referenced file(s) missing: "https://api.which-llm.com/report/wrong_address"
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 20 mutating operations with no state check
- 40Consistency. Frontmatter name (Decision Economic Optimizer) differs from the folder (which-llm)
- 40Execution cost. Instruction body is 8220 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 179 steps, 1 vague phrases
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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)
- +3Description length 95: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -227 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 49 headings
- +3Step-by-step instructions: 179 items
- +4Has examples (31 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.