virbius-mcp-python@1.0.3
CAUTION· install onlyPublisher claims: "VirbiusAgent edge enforcement primitives for Python (PyO3 binding of virbius-core)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
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
VIRBIUS_EDGE_API_KEYConfiguration, not credentials: VIRBIUS_APP_ID, VIRBIUS_CONTROL_BASE_URL, VIRBIUS_DATA_DIR, VIRBIUS_DEVICE_ID, VIRBIUS_EDGE_CACHE_DIR, VIRBIUS_EDGE_MANIFEST_PATH, VIRBIUS_GVISOR_ROOTFS, VIRBIUS_GVISOR_STATE_ROOT, VIRBIUS_RUNSC_PATH, VIRBIUS_TENANT_ID- Where it talks to
- no vendor host named in the codeAlso evil.com, corp.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names evil.com, corp.com as well as its own vendor. The guard injects VIRBIUS_EDGE_API_KEY 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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 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: AWS access key pattern detected; Destructive file system command detected; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
let content = "deploying with key AKIAIOSFODNN7EXAMPLE";Fix: Never read or enumerate credential locations; accept a documented environment variable instead./// Per-step cap for kill / try_wait / `runsc delete`.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."keywords" : [ "demo-deny-keyword-1", "demo-deny-keyword-2", "jailbreak", "ignore previous instructions" ],Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.//! ## Server target formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.MCPServerSse({...}, failure_error_function=virbius_tool_error)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.//! | with a hard deadline (kill on timeout)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.args: json!({"path": "/etc/passwd"}),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."keywords" : [ "demo-deny-keyword-1", "demo-deny-keyword-2", "jailbreak", "ignore previous instructions" ],Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.//! ## Server target formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.//! ## Server target formatFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim i1see1you: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- AWS access key pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
- 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.