Skills/npm/optbrew

optbrew@0.4.0

VERIFIED· install only

Publisher claims: "Pinned search audit and improvement skill bundle" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher nowwcastle-sudo · publishing for 31 daysInstalls 1,754Last detonated 24 min ago
$claude mcp add optbrew -- npx -y optbrew
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 2026-11-14 and scored it 80/100 (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

HIGH
Access to sensitive file pathsskills/optbrew/scripts/core/chrome.mjs:140 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst authChallengeResponse = provide ? { response: 'ProvideCredentials', ...credentials } : { response: 'CancelAuth' };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionskills/optbrew/scripts/audit.mjs:32 · File type combined with upload action — agent may exfiltrate local data files…w new Error('usage: node skills/optbrew/scripts/audit.mjs --context <run-context.json> --modules naver-searchadvisor,magnus-seo --output-dir <run-dir>'); const context = JSON.parse(await readFile(contextPath, 'ut…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Credential pass-through configurationskills/optbrew/scripts/core/render.mjs:78 · Credential pass-through configuration — agent relays sensitive credentials* `transport` is what `selectTransport` returned; the proxy credential only ever travels inside it, in memory.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationskills/optbrew/scripts/core/chrome.mjs:131 · Credential pass-through configuration — agent relays sensitive credentials/** Answer authentication challenges from memory: only a proxy challenge gets the proxy credentials, once per request. */Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
LOW
Refusal suppressionskills/optbrew/references/measurement.md:39 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file… a window is missing, null or unreadable (old evidence, a PageSpeed answer); it never refuses the comparison and adds the warning `cwv_window_unverifiable` to the optional …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionskills/optbrew/scripts/preflight.mjs:119 · File type combined with upload action — agent may exfiltrate local data files// Where /sitemap.xml ended up: WordPress and Yoast send it on to an index file under another name.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandskills/optbrew/scripts/core/keys.mjs:86 · File permission modification command — agent changes file ownership/permissions// Windows has no POSIX modes (chmod only toggles read-only there); the home folder's own ACL protects the file.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionskills/optbrew/scripts/cli.mjs:18 · File type combined with upload action — agent may exfiltrate local data files…le> --after <file> [--fixes <fixes.md>] --output <file> | report --input <packet.json> --output-dir <directory> | runbook --ids <id,id> --level beginner|brief | change start -…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionskills/optbrew/scripts/core/report.mjs:976 · File type combined with upload action — agent may exfiltrate local data filesconst jsonPath = path.resolve(outputDir, 'report.json'), markdownPath = path.resolve(outputDir, 'report.md'), fixesPath = path.resolve(outputDir, FIXES_FILE);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈4,789 tok
1 file · 80 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 optbrew@0.4.0 as of 1 min ago. This is the package itself, not its dependencies.

optbrew@0.4.0 safety verdict: Verified (install only) — KillerSkills