CD vedetta
Buy pay-per-call market intel via x402. Dual rail: Base USDC (live) and Solana /sol/v1/* (live; paid feed settle proven; SVM client for Sol pay).
Buy pay-per-call market intel via x402.
As a process D 44/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 9
-
high Broad scope
meta-requests-env-secretSKILL.md:1Skill asks the runtime to inject credential env vars into its sandbox: VEDETTA_X402_PRIVATE_KEY, VEDETTA_X402_SOLANA_PRIVATE_KEY (high-value: VEDETTA_X402_PRIVATE_KEY, VEDETTA_X402_SOLANA_PRIVATE_KEY) — verify each one is needed for the stated purposerequired_environment_variables: VEDE…KEY, VEDE…KEY
Medium and low: 8
-
medium Risky intent
intent-wallet-secretsSKILL.md:29Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetEnter the private key of the wallet this agent should pay from
-
low Secrets in code
secret-high-entropy-tokenscripts/pay-sol.mjs:65High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)payTo_expected: '4kEd…Hdq',
detector -
low Secrets in code
secret-high-entropy-tokenscripts/pay-sol.mjs:67High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)asset_usdc_mint: 'EPjF…t1v',
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:57High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| **Base** | `/v1/*` | `eip155:8453` | exact / Base | USDC | `0x21…eFA` | **live** |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:58High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| **Solana** | `/sol/v1/*` | `solana:mainnet` | exact on `sola…vdp` | USDC | `4kEd…Hdq` | **live** (paid feed settle proven) |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:71High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- Asset: `2p7B…QJg`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:72High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- Owner / payTo: `4kEd…Hdq`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:73High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- Op wallet: `BKZG…vV3`
quoted
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 145 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
frontmatter-keyunknown frontmatter key "required_environment_variables"
Process rating: all ten parameters 44/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Consistency. Frontmatter name (vedetta) differs from the folder (vedetta-skill)
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 100Steps. 40 steps
- 100Execution cost. Instruction body is 2461 tokens
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -31 of 3 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 145: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.