AC woocommerce-agent-guardrails
Safety guardrails for AI agents writing to a live WooCommerce store via MCP or the REST API — price/bulk-change caps, mandatory approval gates before irreversible writes (deletes, storewide discounts, bulk price updates, publish/unpublish), a dry-run-before-execute workflow with before/after diffs, a circuit breaker on repeated failures, and prompt-injection defense against untrusted product descriptions, reviews, and supplier CSV feeds. Load this automatically for any task that creates, updates, deletes, or bulk-modifies WooCommerce products, prices, inventory, orders, coupons, or customer data — e.g. "update prices for these 200 SKUs," "import this supplier price list," "apply a 20% storewide discount," "delete all out-of-stock products," or any WooCommerce automation touching a production store. Trigger even when the request sounds routine — one unreviewed bulk write can zero out prices or delete live listings before anyone notices.
Safety guardrails for AI agents writing to a live WooCommerce store via MCP or the REST API — price/bulk-change caps, mandatory approval gates before…
As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
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 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2569 tokens
- 100Progress reporting. Reports progress
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)
- +3Description length 949: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.