Skills/npm/a11y-audit-skill

a11y-audit-skill@1.0.0

VERIFIED· install only

Publisher claims: "An accessibility audit skill for coding agents: WCAG 2.2 checks in a real browser, a keyboard-only walk, and verified fixes." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher necromancervbh · publishing for 14 daysInstalls 352Last detonated 6d ago
$claude mcp add a11y-audit-skill -- npx -y a11y-audit-skill
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-08 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packageskills/a11y-audit/SKILL.md:26 · npx invocation of non-well-known package — may execute untrusted codenpx a11y-audit-skill http://localhost:3000 --click "button.open-signin" --out a11y-report/signinFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Image alt text carrying instructionsREADME.md:7 · Image alt text carrying instructions · informational: not an instruction fileThe audit finds 31 issues on a demo shop page and outlines each one on a screenshot; after the fixes, a re-run finds 0Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageskills/a11y-audit/SKILL.md:25 · npx invocation of non-well-known package — may execute untrusted codenpx a11y-audit-skill http://localhost:3000 --out a11y-reportFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/a11y-audit/SKILL.md:18 · npx invocation of non-well-known package — may execute untrusted code0. **Install once** (if `npx a11y-audit-skill --help` fails): `npm install --save-dev a11y-audit-skill && npx playwright install chromium`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageaction.yml:53 · npx invocation of non-well-known package — may execute untrusted codecd "$GITHUB_ACTION_PATH" && npx playwright install --with-deps chromiumFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈961 tok
1 file · 8 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for a11y-audit-skill@1.0.0 as of 6d ago. This is the package itself, not its dependencies.