Skills/npm/expert

expert@0.3.0

CAUTION· install only

Publisher claims: "A blocking second-opinion CLI for agents: GPT-6 Astra in Pro reasoning mode or Gemini 4 Carbon, with resumable background jobs." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher bigblueboo · publishing for 112 daysInstalls 151Last detonated 15 min ago
What would fix thisWatchDispute verdict

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 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. 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 pathsdist/context.js:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env.*",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/context.js:20 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/expert/SKILL.md:132 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Avoid attaching `.env`, credentials, private keys, customer data, build directories, `node_modules`, and unrelated repository snapshots.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/thermo-nuclear-expert-review/scripts/run-review.sh:298 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesNever open files that hold secrets or credentials (.env files, private keys,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packageskills/thermo-nuclear-expert-review/scripts/run-review.sh:330 · npx invocation of non-well-known package — may execute untrusted codeexpert_cmd=(npx -y @bigblueboo/expert)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/thermo-nuclear-expert-review/SKILL.md:54 · npx invocation of non-well-known package — may execute untrusted code`npx -y @bigblueboo/expert` on its own. Run the script from the repository root.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/expert/SKILL.md:20 · npx invocation of non-well-known package — may execute untrusted codeIf `expert` is not on `PATH`, run it via npx — no install required:Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/thermo-nuclear-expert-review/scripts/run-review.sh:586 · npx invocation of non-well-known package — may execute untrusted code# expert >= 0.2.0 reads EXPERT_OPENAI_API_KEY; older CLIs on PATH or in the npxFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsskills/thermo-nuclear-expert-review/SKILL.md:80 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`*.p12`, `*.pfx`, `id_rsa*`, `id_ed25519*`, `.npmrc`, and `.netrc` as secretsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/thermo-nuclear-expert-review/scripts/run-review.sh:318 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessecret_globs=(".env" ".env.*" "*.pem" "*.key" "*.p12" "*.pfx" "id_rsa*" "id_ed25519*" ".npmrc" ".netrc")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandskills/thermo-nuclear-expert-review/scripts/run-review.sh:187 · Process kill command — agent can terminate processeswhile kill -0 "${pids[$i]}" 2>/dev/null; doFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/thermo-nuclear-expert-review/scripts/run-review.sh:168 · Process kill command — agent can terminate processesfor p in ${pids[@]+"${pids[@]}"}; do kill -"$1" -- "-$p" 2>/dev/null || true; doneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionskills/thermo-nuclear-expert-review/scripts/run-review.sh:408 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(d.estimated_input_tokens);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/thermo-nuclear-expert-review/SKILL.md:173 · File type combined with upload action — agent may exfiltrate local data files`<engine>.log`; without `--output-dir` they stay in a temp directory whose pathFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsskills/thermo-nuclear-expert-review/SKILL.md:79 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesGoogle for `gemini`, Anthropic for `claude`. The script treats `.env`, `.env.*`, `*.pem`, `*.key`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packageskills/expert/SKILL.md:23 · npx invocation of non-well-known package — may execute untrusted codenpx -y @bigblueboo/expert ask "Review this implementation for correctness and missing tests." \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionskills/thermo-nuclear-expert-review/SKILL.md:169 · File type combined with upload action — agent may exfiltrate local data files--attach "src/**/*.ts" --attach package.json --output-dir reviews/Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/thermo-nuclear-expert-review/scripts/run-review.sh:193 · Process kill command — agent can terminate processeswhile kill -0 -- "-${pids[$i]}" 2>/dev/null; do sleep 0.2; doneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈5,797 tok
2 files · 23 in bundle

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

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim bigblueboo: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim bigbluebooPropose a patch to the maintainer