BC zoodata
API endpoint reference for the ZooData data platform: the 12 commerce endpoints plus 10 keyword-intelligence endpoints (categories, markets, products, competitors, realtime ASIN, AI review analysis, raw reviews, price band, brand, history, and the keyword detail/trend/extends/search/ market-profile/product-traffic/competitor-keywords/traffic-timeline family) — their inputs/outputs, parameter quirks, Quick Start (auth, base URL), how credits are tracked (meta.creditsConsumed), and the Local Review Toolkit (Map/Reduce for raw reviews). Use when the user asks about the API itself: which endpoints exist, how to call them (e.g. /products/search), field schemas returned by an endpoint, parameter quirks, how to authenticate, how credit consumption is reported, how to get started, or how the Local Review Toolkit works. Requires ZOODATA_API_KEY.
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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Exfiltration
net-redirectable-api-keyscripts/zoodata.py:74Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Secrets in code
secret-high-entropy-tokenreferences/openapi-reference.md:544High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)`sponsoredRecommendImpressionPointPrev`, `firs…rds`,
detector -
low Secrets in code
secret-high-entropy-tokenreferences/openapi-reference.md:545High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)`firs…rds`.
detector -
low Secrets in code
secret-high-entropy-tokenreferences/openapi-reference.md:549High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)`firs…rds` and `firs…rds` items contain
detector -
low Secrets in code
secret-high-entropy-tokenreferences/openapi-reference.md:552High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)`firs…rds` lists keywords newly entering ORG first three pages;
detector -
low Secrets in code
secret-high-entropy-tokenreferences/openapi-reference.md:553High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)`firs…rds` lists keywords that dropped out of ORG first three pages.
detector -
low Secrets in code
secret-high-entropy-tokenSKILL.md:282High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)`sponsoredRecommendImpressionPointPrev`, `firs…rds`,
detector -
low Secrets in code
secret-high-entropy-tokenSKILL.md:283High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)`firs…rds`
detector -
low Secrets in code
secret-high-entropy-tokenSKILL.md:286High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)- `firs…rds` and `firs…rds` are arrays of objects with
detector -
low Secrets in code
secret-high-entropy-tokenSKILL.md:288High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)- `firs…rds` lists keywords newly entering ORG first three pages; `firs…rds`
detector
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8460 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 40Execution cost. Instruction body is 8460 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 161 steps, 1 vague phrases
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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)
- +3Description length 848: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -238 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 28 headings
- +3Step-by-step instructions: 161 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.