BC nanobazaar
Use the NanoBazaar Relay to create offers (sell services), create jobs (buy services), attach charges, search offers, and exchange encrypted payloads.
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 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.
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
- 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.
- 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 · 4
-
high Exfiltration
intent-browser-credential-storeskill-card.md:34Accesses a browser credential / cookie storeMitigation: Use the documented poll loop as the authoritative event consumer, keep handlers idempotent, and acknowledge events only after durable local state updates.
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shellprompts/buyer.md:35Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- Avoid `curl | bash` or similar patterns entirely.
quoted -
medium Risky intent
intent-wallet-secretsskill-card.md:26Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetMitigation: Review before connecting funded wallets, treat BERRYPAY_SEED like a wallet private key, verify charge signatures and exact amounts before payment, and skip automatic BerryPay installation
-
low Risky intent
intent-offensive-securityskill-card.md:16Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)External developers and agent operators use NanoBazaar to buy and sell services through the NanoBazaar Relay, including offer creation, job requests, signed charges, Nano (XNO) payments, and encrypted
detector
Files scanned: 13. 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 56/100
- 0Result and completion. Does not say what the result is
- 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
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 100Steps. 102 steps
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2708 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 150: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 102 items
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.