BD goldkey-agent-utilities
Preflight proposed agent actions with GoldKey Action Gate for a deterministic ALLOW, REVIEW, or BLOCK receipt, or integrate the feature-gated GoldKey Guard beta as an operator-controlled enforcement path for actual MCP, HTTPS, AgentCash, or supported Base/EVM calls. Use for x402-paid action screening, policy enforcement before tool calls or wallet transactions, Guard installation and recovery, component JSON, prompt, URL, spend, and Unicode checks, pass-versus-paygo decisions, or GoldKey pass authentication, quota, and scoped child-key operations.
Preflight proposed agent actions with GoldKey Action Gate for a deterministic ALLOW, REVIEW, or BLOCK receipt, or integrate the feature-gated GoldKey Guard…
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Dangerous commands
cmd-install-from-urlreferences/guard-beta.md:70Installs a package from an untrusted URL / archive (documentation of a security skill)npm install --ignore-scripts /absolute/private/gold…tgz
security skill -
medium Risky intent
intent-wallet-secretsreferences/pass-and-keys.md:25Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetTreat every returned transaction as unsigned. Independently verify chain, target, value, calldata purpose, exact USDC approval, sequence, expiry, and the current spend mandate before signing. Never re
-
low Secrets in code
secret-high-entropy-tokenscripts/goldkey-client.mjs:8High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const BASE_MAINNET_USDC = "0x83…913";
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/goldkey-client.mjs:9High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const PAYGO_TREASURY = "0xd6…b1b";
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/goldkey-client.mjs:21High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)contract: "0x22…db0",
quoted -
low Obfuscation
obf-base64-blobskill-card.md:44Long base64-looking blob (documentation of a security skill)- [Action Gate Poncho Listing](https://tryponcho.com/tool/url_…0ZQ)
security skill -
low Obfuscation
obf-base64-blobSKILL.md:50Long base64-looking blob (documentation of a security skill)- Poncho: <https://tryponcho.com/tool/url_…0ZQ>
security skill -
low Risky intent
intent-wallet-secretsSKILL.md:112Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)Give the returned `payment_required` to the caller's installed x402 wallet tool and let that tool sign and settle under its own mandate. This bundle never accepts a wallet private key or fabricates pa
quoted
Files scanned: 6. 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 49/100
- 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. 1 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (goldkey-agent-utilities) differs from the folder (goldkey)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 15 steps
- 100Execution cost. Instruction body is 2528 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +3Description length 553: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.