CD heurist-mesh-skill
Real-time crypto token data, DeFi analytics, blockchain data, Twitter/X social intelligence, enhanced web search, crypto project search all in one Skill. For in-depths topics, "Ask Heurist" agent can handle market trends, trading strategies, macro news, and deep research.
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 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.
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.
- 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 · 9
-
high Dangerous commands
cmd-pipe-to-shellreferences/x402-payment.md:8Downloads and executes remote code from an unrecognised host (pipe to shell)curl -L https://foundry.paradigm.xyz | bash
Medium and low: 8
-
medium Exfiltration
net-credential-usereferences/inflow-payment.md:81Credential used in a network call (verify the destination is the intended service)curl -sS -H "X-API-Key: $INFLOW_PRIVATE_KEY" \
-
medium Dangerous commands
cmd-pipe-to-shellreferences/x402-payment.md:123Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- `cast` from Foundry (`curl -L https://foundry.paradigm.xyz | bash && foundryup`)
quoted -
medium Risky intent
intent-wallet-secretsSKILL.md:71Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target1. You need a wallet private key with USDC balance on Base.
-
medium Risky intent
intent-wallet-secretsSKILL.md:100Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetOnce you have either Heurist API key or x402 wallet private key or Inflow key, you can make API calls. You should understand the tool schema and the parameters of tools you want before calling it.
-
low Secrets in code
secret-high-entropy-tokenreferences/x402-payment.md:31High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"payTo": "0x7d…05D",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/x402-payment.md:34High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"asset": "0x83…913",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/x402-payment.md:72High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"verifyingContract": "0x83…913"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/x402-payment.md:122High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- USDC contract: `0x83…913`
quoted
Files scanned: 6. 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")
Process rating: all ten parameters 45/100
- 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. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (heurist-mesh-skill) differs from the folder (heurist-mesh)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 100Steps. 34 steps
- 100Execution cost. Instruction body is 1518 tokens
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
- +1No license
- +2Single-language instructions
- +3Description length 272: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.