BC agentwalletapi
OpenclawCash crypto wallet API for AI agents (also called openclawcash). Use when an agent needs to send native or token transfers, check balances, list wallets, or interact with EVM and Solana wallets programmatically via OpenclawCash.
As a process C 58/100 · Has gaps — weak spots: result and completion, consistency, running it twice
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
- 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 · 11
✓ No critical or high findings
Medium and low: 11
-
medium Exfiltration
net-credential-usescripts/agentwalletapi.sh:245Credential used in a network call (verify the destination is the intended service)curl -s -H "X-Agent-Key: $AGENTWALLETAPI_KEY" \
-
medium Exfiltration
net-credential-usescripts/agentwalletapi.sh:250Credential used in a network call (verify the destination is the intended service)curl -s -H "X-Agent-Key: $AGENTWALLETAPI_KEY" \
-
medium Exfiltration
net-credential-usescripts/agentwalletapi.sh:281Credential used in a network call (verify the destination is the intended service)curl -s -H "X-Agent-Key: $AGENTWALLETAPI_KEY" \
-
medium Exfiltration
net-credential-usescripts/agentwalletapi.sh:378Credential used in a network call (verify the destination is the intended service)curl -s -H "X-Agent-Key: $AGENTWALLETAPI_KEY" \
-
low Secrets in code
secret-high-entropy-tokenreferences/api-endpoints.md:416High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded){ "walletId": 2, "to": "0xRe…...", "token": "0xA0…B48", "valueBaseUnits": "100000000" }quoted -
low Secrets in code
secret-high-entropy-tokenreferences/api-endpoints.md:421High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded){ "walletId": 2, "to": "0xRe…...", "token": "0xA0…B48", "amountDisplay": "100" }quoted -
low Secrets in code
secret-high-entropy-tokenreferences/api-endpoints.md:1035High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"userAddress": "0x49…0a5",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/api-endpoints.md:1142High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"tokenAddress": "0xA0…B48",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/api-endpoints.md:1143High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"spender": "0x7a…88D",
quoted -
low Exfiltration
net-credential-usescripts/agentwalletapi.sh:308Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)BODY="{\"label\":\"$LABEL_ESC\",\"network\":\"$NETWORK_ESC\",\"exportPassphrase\":\"$PASSPHRASE_ESC\",\"exportPassphraseStorageType\":\"env\",\"exportPassphraseStorageRef\":\"$PASSPHRASE_ENV_ESC\",\"cquoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:383High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded){ "walletId": "Q7X2K9P", "to": "0xRe…...", "token": "0xA0…B48", "amountDisplay": "100" }quoted
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6600 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 35 mutating operations with no state check
- 40Consistency. Frontmatter name (agentwalletapi) differs from the folder (open-claw-cash)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6600 tokens
- 100Steps. 186 steps
- 100Failures and branches. 10 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 19 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 236: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 186 items
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.