BC disinto
Operate the disinto autonomous code factory. Use when managing factory agents, filing issues on the forge, reading agent journals, querying CI pipelines, checking the dependency graph, or inspecting factory health.
As a process C 64/100 · Has gaps — weak spots: result and completion, when it triggers, 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-credential-usescripts/factory-status.sh:40Credential used in a network call (verify the destination is the intended service)curl -sf -H "Authorization: token ${FORGE_TOKEN}" \ -
medium Exfiltration
net-credential-usescripts/factory-status.sh:101Credential used in a network call (verify the destination is the intended service)pipelines=$(curl -sf -H "Authorization: Bearer ${WOODPECKER_TOKEN}" \ -
medium Exfiltration
net-credential-usescripts/file-issue.sh:44Credential used in a network call (verify the destination is the intended service)all_labels=$(curl -sf -H "Authorization: token ${FORGE_TOKEN}" \ -
medium Exfiltration
net-credential-useSKILL.md:154Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer ${WOODPECKER_TOKEN}" \ -
low Exfiltration
net-credential-usescripts/read-journal.sh:62Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)echo " curl -sH 'Authorization: token \${FORGE_TOKEN}' '\${FORGE_API}/issues?state=open&labels=prediction%2Fun…wed'"quoted
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "env_vars" - note
frontmatter-keyunknown frontmatter key "tools"
Process rating: all ten parameters 64/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1524 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
- +2Single-language instructions
- +3Description length 214: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (8 code blocks)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.