CF chainstream-defi
[FINANCIAL EXECUTION] Execute irreversible on-chain DeFi operations via CLI and MCP tools. Use when user wants to swap tokens, create tokens on launchpad, sign transactions, broadcast signed transactions, or execute trading strategies. Requires explicit user confirmation before every destructive operation. All transactions are real and irreversible. Keywords: swap, DEX, launchpad, transaction, trade, sign, broadcast, PumpFun, Jupiter, Uniswap, USDC, SOL, execute.
As a process F 57/100 · Will not run — References files that are not bundled: ../chainstream-data/, ../shared/authentication.md, ../shared/authentication.md
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.
- 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 · 16
-
high Dangerous commands
cmd-pipe-to-shellshared/authentication.md:207Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://tempo.xyz/install | bash
Medium and low: 15
-
medium Risky intent
intent-wallet-secretsreferences/swap-protocol.md:76Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetCLI `wallet sign`: deserialize → sign with wallet private key → encode signed RLP → base64.
-
medium Risky intent
intent-wallet-secretsshared/authentication.md:20Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target| Own wallet private key | CLI with `wallet set-raw` | CLI signs with imported key | x402 (USDC on Base/Solana) |
-
low Secrets in code
secret-high-entropy-tokenreferences/currency-resolution.md:9High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| sol | SOL | `So11…112` |
table -
low Secrets in code
secret-high-entropy-tokenreferences/currency-resolution.md:10High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| sol | USDC | `EPjF…t1v` |
table -
low Secrets in code
secret-high-entropy-tokenreferences/currency-resolution.md:14High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| eth | USDC | `0xA0…B48` |
table -
low Secrets in code
secret-high-entropy-tokenreferences/currency-resolution.md:21High-entropy token-like string (may be an id, hash or a credential) (placeholder value)npx @chainstream-io/cli dex route --chain sol --from <wallet> --input-token So11…112 --output-token <addr> --amount 1000000
placeholder -
low Risky intent
intent-wallet-secretsshared/authentication.md:32Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)For agents that don't have their own wallet. CLI creates a ChainStream TEE wallet on first login — no email, no registration form, no seed phrase.
quoted -
low Secrets in code
secret-high-entropy-tokenshared/chains.md:17High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| sol | SOL | `So11…112` | `EPjF…t1v` |
table -
low Secrets in code
secret-high-entropy-tokenshared/chains.md:19High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| eth | ETH | `0x00…000` | `0xA0…B48` |
table -
low Secrets in code
secret-high-entropy-tokenshared/chains.md:33High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Solana | Base58, 32-44 chars | `So11…112` |
table -
low Secrets in code
secret-high-entropy-tokenshared/chains.md:34High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| EVM (bsc/eth) | `0x` + 40 hex chars | `0x83…913` |
table -
low Secrets in code
secret-high-entropy-tokenshared/x402-payment.md:118High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **Base**: mainnet — USDC (`0x83…913`), chain ID `eip155:8453`
quoted -
low Secrets in code
secret-high-entropy-tokenshared/x402-payment.md:119High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **Solana**: mainnet — USDC (`EPjF…t1v`)
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:184High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| sol | SOL | `So11…112` | `EPjF…t1v` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:186High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| eth | ETH | `0x00…000` | `0xA0…B48` |
table
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../chainstream-data/ - warning
missing-refreference to a missing file: ../shared/authentication.md - warning
missing-refreference to a missing file: ../shared/authentication.md - warning
missing-refreference to a missing file: ../shared/x402-payment.md - warning
missing-refreference to a missing file: ../chainstream-graphql/
Process rating: all ten parameters 57/100
- 0Tools and files. 5 referenced file(s) missing: ../chainstream-data/, ../shared/authentication.md, ../shared/authentication.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 28 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2933 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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
- +1No license
- +2Single-language instructions
- +3Description length 467: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.