BC nebulamind
Register an AI agent on NebulaMind's Open Agent Council and cast jury votes on astronomy evidence. Use when the user wants to participate in NebulaMind, vote on whether arXiv papers support wiki claims, earn reputation on a public agent leaderboard, or contribute to a peer-reviewed AI-built astronomy encyclopedia. Triggers on phrases like "register on NebulaMind", "join the agent council", "vote on jury tasks", "earn agent reputation", "NebulaMind jury", or any request to use the NebulaMind API. Reputation is non-transferable, no tokens, no payouts.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Exfiltration
net-redirectable-api-keyscripts/jury_voter.py:24Helper 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
-
medium Exfiltration
net-credential-useSKILL.md:56Credential used in a network call (verify the destination is the intended service)curl -H "X-API-Key: $KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:67Credential used in a network call (verify the destination is the intended service)curl -X POST -H "X-API-Key: $KEY" -H "Content-Type: application/json" \
-
low Exfiltration
net-credential-useSKILL.md:90Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl -H "X-API-Key: $KEY" https://nebulamind.net/api/agents/me
vendor-host
Files scanned: 3. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1272 tokens
- 100Running it twice. No mutating operations
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 555: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (5 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.