BB autonomous-agent
CornerStone MCP x402 skill for agents. Tools for stock predictions, backtests, bank linking, and agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, get_agent_reputation_score, get_borrower_score, by-email variants) with x402 flow (Aptos + Base). Skill handles 402 → pay → retry. Wallet attestation for onboarding. For marketplaces where agents download and use skills autonomously.
As a process B 66/100 · Nearly there — weak spots: result and completion, when it triggers
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 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.
How to improve
- 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 · 11
✓ No critical or high findings
Medium and low: 11
-
medium Exfiltration
net-redirectable-api-keysrc/agent/llm.js:9Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:40High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…nFR+MDik6udKfj2+9ZsmTLV0/t73v…I7L+1+yjEbQ==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:74High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…sgO+fnZo…ZmP+IDCXRtU/g==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:84High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…Hjp+geiw…y6u/TqkU…7R5/SMQ==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:149High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…TV6+QnX7…16S+X8zp…N8w==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:420High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…yhZ++8YtiK9d/3DBK…59X/P1Pf…EIg==",
detector -
low Risky intent
intent-wallet-secretssrc/lib/aptos/signPayment.js:38Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)'Aptos wallet private key is missing or invalid (expected 64 hex chars). Run setup-aptos.js or create_aptos_wallet first.'
quoted -
low Secrets in code
secret-high-entropy-tokensrc/lib/evm/signPayment.js:11High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const BASE_SEPOLIA_USDC = process.env.BASE_SEPOLIA_USDC || '0x03…F7e';
quoted -
low Secrets in code
secret-high-entropy-tokensrc/swap.js:7High-entropy token-like string (may be an id, hash or a credential)* node src/swap.js base eth 0x83…913 0.01
-
low Secrets in code
secret-high-entropy-tokensrc/swap.js:67High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)node src/swap.js base eth 0x83…913 0.01 # Swap 0.01 ETH → USDC on Base
quoted -
low Secrets in code
secret-high-entropy-tokensrc/swap.js:68High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)node src/swap.js base 0x83…913 eth 100 # Swap 100 USDC → ETH on Base
quoted
Files scanned: 48. 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 66/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 61 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2353 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (5 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
- +2Single-language instructions
- +3Description length 431: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 61 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.