langsys-skill@0.3.4
VERIFIED· install onlyPublisher claims: "Portable agent skill for integrating and migrating projects onto the Langsys SDKs — works in Claude Code, Codex, Gemini CLI and Cursor." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry npm (MCP server)Publisher langsys · publishing for 86 daysInstalls 795Last detonated 4d ago
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 2026-11-10 and scored it 84/100 (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 deviationst+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
File type combined with upload actionsrc/bin/scan.mjs:971 · File type combined with upload action — agent may exfiltrate local data files
AST07console.log(` Public site? Prefer a runtime adapter — only SSR puts CURRENT`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.HIGH
Access to sensitive file pathssrc/bin/doctor.mjs:441 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05// ── .env inspection ──────────────────────────────────────────────────────────Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
npx invocation of non-well-known packagesrc/bin/install.mjs:12 · npx invocation of non-well-known package — may execute untrusted code
AST06* npx langsys-skill install --dry-runFix: Pin versions and sources; vendor anything fetched at install time.MEDIUM
File type combined with upload actionsrc/bin/scan.mjs:989 · File type combined with upload action — agent may exfiltrate local data files
AST07console.log(`\n The base-locale catalog is a REQUIRED INPUT, not a reference. Langsys uses the`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.MEDIUM
npx invocation of non-well-known packagesrc/bin/install.mjs:10 · npx invocation of non-well-known package — may execute untrusted code
AST06* npx langsys-skill install --global # user scopeFix: Pin versions and sources; vendor anything fetched at install time.LOW
Instructs the agent to modify its persistent memory or instruction filessrc/bin/drift-guard.mjs:437 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
AST01// CLAUDE.md, no prompt to update the README (not fixed until 0.5.0), and noFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.MEDIUM
npx invocation of non-well-known packagesrc/bin/doctor.mjs:282 · npx invocation of non-well-known package — may execute untrusted code
AST06`Run \`npx langsys-skill install\` to copy ${skills.map((s) => s.name).join(', ')} ` +Fix: Pin versions and sources; vendor anything fetched at install time.HIGH
Access to sensitive file pathssrc/bin/doctor.mjs:443 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05const envFiles = ['.env', '.env.local', '.env.development', '.env.production']Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
npx invocation of non-well-known packagesrc/bin/install.mjs:11 · npx invocation of non-well-known package — may execute untrusted code
AST06* npx langsys-skill install --host=claude,codexFix: Pin versions and sources; vendor anything fetched at install time.MEDIUM
npx invocation of non-well-known packagesrc/bin/doctor.mjs:325 · npx invocation of non-well-known package — may execute untrusted code
AST06'Re-run `npx langsys-skill install`. Until then the skill documents a version you do not have.');Fix: Pin versions and sources; vendor anything fetched at install time.MEDIUM
npx invocation of non-well-known packagesrc/bin/doctor.mjs:321 · npx invocation of non-well-known package — may execute untrusted code
AST06`${rec.package} ${live.installed} is installed now. Re-run \`npx langsys-skill install\` ` +Fix: Pin versions and sources; vendor anything fetched at install time.MEDIUM
npx invocation of non-well-known packagesrc/bin/scan.mjs:1099 · npx invocation of non-well-known package — may execute untrusted code
AST06console.log(` npx langsys-doctor`);Fix: Pin versions and sources; vendor anything fetched at install time.MEDIUM
npx invocation of non-well-known packagesrc/bin/install.mjs:9 · npx invocation of non-well-known package — may execute untrusted code
AST06* npx langsys-skill install # project scope, auto-detect hostsFix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Instructions loaded
≈2,836 tok
1 file · 71 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 langsys-skill@0.3.4 as of 4d ago. This is the package itself, not its dependencies.