BB lg-thinq-universal
Universal LG ThinQ device manager. Discovers appliances (AC, Refrigerator, Washer, etc.) and generates secure, device-specific OpenClaw skills. Use when the user wants to: (1) Integrate LG ThinQ devices, (2) Know how to get an LG PAT token, (3) Discover new LG appliances, (4) Create specialized control skills for their home automation.
As a process B 65/100 · Nearly there — weak spots: result and completion, running it twice
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 files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
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
- 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 Secrets in code
secret-labelled-tokenreferences/api-reference.md:99Labelled token / key literal (vendor format unknown — verify it is not a live credential)x-api-key: v6GF…SR3
-
medium Exfiltration
net-redirectable-api-keyscripts/generate_control_script.py:68Helper 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/api-reference.md:25High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `x-api-key` | Yes | Fixed: `v6GF…SR3` |
table -
low Secrets in code
secret-high-entropy-tokenreferences/api-reference.md:75High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `LG_API_KEY` | `v6GF…SR3` | Fixed API key |
table -
low Secrets in code
secret-high-entropy-tokenreferences/api-reference.md:99High-entropy token-like string (may be an id, hash or a credential)x-api-key: v6GF…SR3
-
low Secrets in code
secret-password-literalreferences/api-reference.md:99Hard-coded password / key literal (may be an example)x-api-key: v6GF…SR3
-
low Secrets in code
secret-high-entropy-tokenreferences/device-example.md:56High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)"x-api-key": "v6GF…SR3",
fixturequoted -
low Secrets in code
secret-high-entropy-tokenreferences/public_api_constants.json:1High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded){"NOTE": "These are public LG Developer Kit constants, not private secrets", "LG_API_KEY": "v6GF…SR3", "LG_CLIENT_ID": "test…456", "LG_MESSAGE_ID": "fNvdZ1brTquoted
Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Universal LG ThinQ device manager. Discovers appliances (AC, Refri… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1240 tokens
- 100Progress reporting. Reports progress
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
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 337: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 24 items
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.