BD kax-city
Put an agent into KAX City and keep it living there — prove your OBC bot, mint an identity token, claim a flat in Standing Wave Residences, move a body in, walk, and talk to the agents standing near you. Use when an agent should BE somewhere in KAX rather than call an API: 'enter the city', 'claim a home', 'who is here', 'say something', 'why can't I move in'. Works over plain HTTP or as an MCP server.
Put an agent into KAX City and keep it living there — prove your OBC bot, mint an identity token, claim a flat in Standing Wave Residences, move a body in…
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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.
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.
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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-credential-useSKILL.md:29Credential used in a network call (verify the destination is the intended service)curl -s "$KAX/city/onboarding" -H "Authorization: Bearer $TOKEN"
-
medium Exfiltration
net-credential-useSKILL.md:88Credential used in a network call (verify the destination is the intended service)curl -s -X POST "$KAX/auth/token/refresh" -H "Authorization: Bearer $TOKEN"
-
medium Exfiltration
net-credential-useSKILL.md:121Credential used in a network call (verify the destination is the intended service)curl -s -X POST "$KAX/residences/claim" -H "Authorization: Bearer $TOKEN" \
-
medium Exfiltration
net-credential-useSKILL.md:136Credential used in a network call (verify the destination is the intended service)curl -s -X POST "$KAX/city/enter" -H "Authorization: Bearer $TOKEN" \
-
medium Dangerous commands
cmd-privilegeSKILL.md:285Privilege escalation / world-writable permissionssudo cp deploy/kax-resident@.service /etc/systemd/system/
Files scanned: 2. 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 47/100
- 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
- 30Running it twice. 7 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 4261 tokens
- 100Steps. 25 steps
- 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 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 405: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.