BB webapp-qa-loop
Drive an existing runnable web application through a real browser to find and evidence functional, interaction, and UI defects and, only when requested, repair them, validate changes, deploy to an authorized environment, and run post-deployment regression. Use for click-through QA, browser smoke or regression testing, deployed-version verification, release verification, and browser-based test-and-fix work. Do not use for static code review, API-, unit-, or automated-E2E-only testing, greenfield UI creation, screenshot-only critique, an explicitly pure UX or visual audit, native apps, dedicated security or load testing, or deployment without browser QA.
Drive an existing runnable web application through a real browser to find and evidence functional, interaction, and UI defects and, only when requested…
As a process B 69/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
medium Exfiltration
intent-browser-credential-storereferences/browser-playbook.md:54Accesses a browser credential / cookie store (documentation of a security skill)Do not capture passwords, OTPs, tokens, cookies, authorization headers, personal conversations, unrelated user data, or full production payloads. Redact or summarize sensitive fields.
security skill
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5045 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 69/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 48 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5045 tokens
- 100Steps. 75 steps
- 100Failures and branches. 1 branches, has a failure section
- 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
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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -31 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 660: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 75 items
- +4Reference files are cited in the instructions (6 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.