BC invoice
Creates and manages invoices as JSON files on GitHub with sequential numbering, preview, and upload.
As a process C 58/100 · 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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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-credential-usescripts/get-invoices.sh:24Credential used in a network call (verify the destination is the intended service)RESPONSE=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
-
medium Exfiltration
net-credential-usescripts/get-invoices.sh:38Credential used in a network call (verify the destination is the intended service)RESPONSE=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
-
medium Exfiltration
net-credential-usescripts/get-next-number.sh:23Credential used in a network call (verify the destination is the intended service)RESPONSE=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
-
medium Exfiltration
net-credential-usescripts/push-invoice.sh:33Credential used in a network call (verify the destination is the intended service)RESPONSE=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 13 mutating operations with no state check
- 40Consistency. Frontmatter name (invoice) differs from the folder (netsnek-invoice)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 100Steps. 45 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2830 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 100: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 20 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (8 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.