BC noya-agent-skill
Interact with the Noya AI platform for crypto trading, prediction markets, token analysis, DCA strategies, and structured crypto data (prices, TVL, funding rates, on-chain analytics, sentiment, news) via curl. Use when the user wants to trade tokens, check portfolios, analyze markets, manage DCA strategies, interact with Polymarket/Rain prediction markets, or pull deterministic crypto data without hitting the agent graph.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
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 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.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
✓ No critical or high findings
Medium and low: 9
-
medium Exfiltration
net-credential-useSKILL.md:115Credential used in a network call (verify the destination is the intended service)curl -s -H "x-api-key: $NOYA_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:235Credential used in a network call (verify the destination is the intended service)curl -s -H "x-api-key: $NOYA_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:242Credential used in a network call (verify the destination is the intended service)curl -s -H "x-api-key: $NOYA_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:249Credential used in a network call (verify the destination is the intended service)curl -s -X DELETE -H "x-api-key: $NOYA_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:256Credential used in a network call (verify the destination is the intended service)curl -s -H "x-api-key: $NOYA_API_KEY" \
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:328High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Token pools | POST | `/geckoterminal/token-pools` | `{ "network": "eth", "tokenAddress": "0xC0…Cc2" }` |table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:329High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Pool OHLCV candles | POST | `/geckoterminal/pool-ohlcv` | `{ "network": "eth", "poolAddress": "0x88…640", "timeframe": "day", "limit": 7 }` |table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:330High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Pool trades | POST | `/geckoterminal/pool-trades` | `{ "network": "eth", "poolAddress": "0x88…640" }` |table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:332High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Token info + top pools | POST | `/geckoterminal/token-info` | `{ "network": "eth", "addresses": ["0xC0…Cc2"] }` |table
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8880 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 59/100
- 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
- 30Running it twice. 15 mutating operations with no state check
- 40Execution cost. Instruction body is 8880 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 54 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 425: enough signal without eating the budget
- +4Structure: 53 headings
- +3Step-by-step instructions: 54 items
- +3Output format is stated explicitly
- +4Has examples (39 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.