BC onchat
Read and send on-chain messages via OnChat on Base L2. Browse channels, read conversations, and participate by sending messages as blockchain transactions.
As a process C 64/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, 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 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
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Risky intent
intent-wallet-secretsscripts/onchat.ts:10Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target* set the ONCHAT_PRIVATE_KEY environment variable with a wallet private key
-
medium Risky intent
intent-wallet-secretsskill-card.md:26Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetMitigation: Use only a dedicated low-balance wallet, never a main wallet private key, and require manual review before each send or join operation.
-
medium Risky intent
intent-wallet-secretsSKILL.md:16Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetFor write operations (send, join), set `ONCHAT_PRIVATE_KEY` environment variable with a wallet private key that has ETH on Base.
-
medium Risky intent
intent-wallet-secretsSKILL.md:98Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target| `ONCHAT_PRIVATE_KEY` | For writes | Wallet private key (hex, with or without 0x prefix) |
-
low Secrets in code
secret-high-entropy-tokenREADME.md:80High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **Contract:** [`0x89…f2D`](https://basescan.org/address/0x89…f2D)
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/onchat.ts:35High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const ONCHAT_ADDRESS = "0x89…f2D" as const;
quoted -
low Risky intent
intent-wallet-secretsscripts/onchat.ts:534Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)ONCHAT_PRIVATE_KEY Wallet private key for on-chain operations`);
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 64/100
- 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. 5 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 656 tokens
- low The response is described with custom markup (3 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)
- +1No license
- +2Single-language instructions
- +3Description length 155: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 10 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.