BC unifi
Query and monitor a UniFi network using a UniFi Integration API key (X-API-KEY) plus compatible read-only classic UniFi Network endpoints. Use when the user asks to check UniFi, list UniFi devices, show who is on the network, inspect UniFi clients, review UniFi health, list sites, review WLANs/networks, check alarms, inspect top apps/DPI availability, or get a UniFi dashboard/overview from a Cloud Gateway or UniFi OS console.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Exfiltration
net-credential-usescripts/health.sh:11Credential used in a network call (verify the destination is the intended service)SITE_JSON=$(curl -sk -H "X-API-KEY: $UNIFI_TOKEN" -H "Accept: application/json" "$UNIFI_URL/proxy/network/integration/v1/sites")
-
medium Exfiltration
net-credential-usescripts/health.sh:14Credential used in a network call (verify the destination is the intended service)DEVICES=$(curl -sk -H "X-API-KEY: $UNIFI_TOKEN" -H "Accept: application/json" "$UNIFI_URL/proxy/network/integration/v1/sites/$SITE_ID/devices?limit=200")
-
medium Exfiltration
net-credential-usescripts/health.sh:15Credential used in a network call (verify the destination is the intended service)CLIENTS=$(curl -sk -H "X-API-KEY: $UNIFI_TOKEN" -H "Accept: application/json" "$UNIFI_URL/proxy/network/integration/v1/sites/$SITE_ID/clients?limit=$CLIENT_LIMIT")
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 51/100
- 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (unifi) differs from the folder (unifi-inforjota-integration)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 35 steps
- 100Execution cost. Instruction body is 845 tokens
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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 429: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.