BB dashpass
Encrypted credential vault on Dash Platform for AI agents. Store and retrieve API keys, tokens, and passwords — encrypted on-chain, decryptable only by you. Triggers on: credential management, password vault, API key storage, secret store, Dash Platform credentials.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions
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
- 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 Risky intent
intent-wallet-secretsscripts/dashpass-cli.mjs:26Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target* CRITICAL_WIF — wallet private key (WIF format)
-
low Secrets in code
secret-high-entropy-tokenreferences/cli-commands.md:281High-entropy token-like string (may be an id, hash or a credential)Contract: ATam…ikq
-
low Secrets in code
secret-high-entropy-tokenreferences/cli-commands.md:282High-entropy token-like string (may be an id, hash or a credential)Identity: 36Sx…6hh
-
low Secrets in code
secret-high-entropy-tokenreferences/cli-commands.md:390High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `DASHPASS_IDENTITY_ID` | **Yes** | Your Dash Platform Identity ID (base58). Determines which identity signs transactions and which credentials you can access. | `36Sx…j7x
table -
low Secrets in code
secret-high-entropy-tokenreferences/cli-commands.md:391High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `DASHPASS_CONTRACT_ID` | No | The Data Contract ID to use. Defaults to the shared testnet contract `GCeh…DQF`. Set this if you deploy your own contract. | `ATamKo
table -
low Secrets in code
secret-high-entropy-tokenscripts/dashpass-cli.mjs:8High-entropy token-like string (may be an id, hash or a credential)* Contract: GCeh…DQF (v2)
-
low Secrets in code
secret-high-entropy-tokenscripts/dashpass-cli.mjs:55High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const DEFAULT_CONTRACT_ID = 'GCeh…DQF';
quoted -
low Secrets in code
secret-anthropic-keyscripts/dashpass-recovery.test.mjs:52Anthropic API key (placeholder value)const secret = { value: 'sk-ant-TESTNET-fake-credential', meta: { service: 'anthropic-api' } };placeholder -
low Secrets in code
secret-high-entropy-tokensetup.md:53High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)3. Getting back an **Identity ID** — a base58 string like `36Sx…6hh`
quoted -
low Secrets in code
secret-high-entropy-tokensetup.md:156High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)export DASHPASS_IDENTITY_ID="36Sx…6hh"
quoted -
low Secrets in code
secret-high-entropy-tokensetup.md:159High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)# export DASHPASS_CONTRACT_ID="ATam…ikq"
quoted
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4107 tokens
- 100Steps. 39 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 12 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
- -33 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 266: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (4 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.