zombiehunter@1.0.0
CAUTION· startup onlyPublisher claims: "Enables autonomous DevOps agents to detect out-of-band AWS resources, calculate monthly FinOps burn, and generate Terraform/OpenTofu import blocks or safe purge scripts through hardened MCP tools." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-16 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Hidden zero-width characters detected; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 20 s · 2 scenarios · 0 deviationsStatic findings
&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.'.env',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.arguments: { filePath: '../../.env' }Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.arguments: { from: 'tfstate://state.json; rm -rf /' }Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.'subdir/../.env'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Type == 'aws_s3' && cat /etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."aws_s3_bucket; rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.arguments: { from: 'tfstate://state.json; rm -rf /' }Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.let md = `# 🧟♂️ EXECUTIVE FINOPS & CLOUD GOVERNANCE AUDITFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.assert.strictEqual(traversalRes.error !== undefined, true, 'MCP muss Traversal-Angriff auf .env abwehren');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.id: 'AKIAIOSFODNN7EXAMPLE',Fix: Never read or enumerate credential locations; accept a documented environment variable instead."aws_s3_bucket; rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.() => generateZombiePurgeScripts([{ type: 'aws_nat_gateway', id: 'nat-123; rm -rf /', monthlyCost: 32 }]),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.🧟♂️ ZombieHunter CLI – FinOps Cloud Governance & Shadow IT HunterFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.assert.strictEqual(masked.includes('AKIAIOSFODNN7EXAMPLE'), false, 'AWS Access Key darf nicht unmaskiert bleiben');Fix: Never read or enumerate credential locations; accept a documented environment variable instead.assert.strictEqual(responseText.includes('AKIAIOSFODNN7EXAMPLE'), false, 'Kein Klartext-AWS-Key im MCP-Output');Fix: Never read or enumerate credential locations; accept a documented environment variable instead.RUN chmod -R +x ./bin || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.'.env.production',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose./^\.env(\..+)?$/i,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.AWS_ACCESS_KEY_ID: AKIAIOSFODNN7EXAMPLEFix: Never read or enumerate credential locations; accept a documented environment variable instead.() => generateZombiePurgeScripts([{ type: 'aws_nat_gateway', id: 'nat-123; rm -rf /', monthlyCost: 32 }]),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim tastenkasperle: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Destructive command against a filesystem root or device≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.