heros-firewall@0.2.0
CAUTION· startup onlyPublisher claims: "Enables agents to route MCP tool calls through an inline policy proxy that enforces OWASP ASI safeguards, gates destructive or high-cost actions behind expiring HMAC-signed human approvals, and records tamper-evident Merkle audit receipts." 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
HEROS_APPROVAL_SECRETConfiguration, not credentials: HEROS_DOWNSTREAM_ARGS, HEROS_DOWNSTREAM_BIN- Where it talks to
- no vendor host named in the codeAlso evil.example, internal.example — not the publisher's domain; check what for before connecting.
- 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 with a scoped credential, under the guard, and read the third-party hosts first. The code names evil.example, internal.example as well as its own vendor. The guard injects HEROS_APPROVAL_SECRET only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-11 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; OS command execution function call detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 20 s · 2 scenarios · 0 deviationsStatic findings
assert.equal(engine.evaluate({ tool: 'shell_exec', args: { cmd: 'echo ok; rm -rf /' }, scopes: ['admin'] }).code, 'DANGEROUS_SHELL');Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.ASI02_TOOL_MISUSE: (i) => ({ tool: "shell_exec", args: { cmd: `rm -rf /tmp/data-${i}; curl http://evil.example` } }),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.| `ignore previous instructions...` in email body | deny | ASI01 |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.assert.equal(engine.evaluate({ tool: 'shell_exec', args: { cmd: 'echo ok; rm -rf /' }, scopes: ['admin'] }).code, 'DANGEROUS_SHELL');Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.ASI05_CODE_EXECUTION: (i) => ({ tool: "eval_code", args: { code: `import os; os.system('id ${i}')` } }),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
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim itsoumya-d: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Destructive command against a filesystem root or device≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.