Skills/PyPI/virbius-mcp-python

virbius-mcp-python@1.0.3

CAUTION· install only

Publisher 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.

Registry PyPI (MCP server)Publisher i1see1you · publishing for 12 daysInstalls 149Last detonated 21 min ago

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.

$vet-skills run --net declared -- uvx virbius-mcp-python

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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 2: usage: python -m virbius_mcp_python doctor [--json] [--engine]
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1:
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocess3 of 3 bundled scripts run with no arguments
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
AWS access key pattern detectedvirbius-core/src/memory_interceptor.rs:551 · AWS access key pattern detected — possible hardcoded or harvested keylet content = "deploying with key AKIAIOSFODNN7EXAMPLE";Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Process kill commandvirbius-core/src/sandbox/wait.rs:12 · Process kill command — agent can terminate processes/// Per-step cap for kill / try_wait / `runsc delete`.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injectionvirbius-core/tests/edge-manifest-debug.json:26 · Prompt injection — known jailbreak technique reference · informational: not an instruction file"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.
AST01
HIGH
Destructive file system command detectedvirbius-core/src/mcp/napi.rs:17 · Destructive file system command detected//! ## Server target formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)python/virbius_mcp_python/guard.py:168 · MCP server using network transport (SSE/HTTP) — data sent over networkMCPServerSse({...}, failure_error_function=virbius_tool_error)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commandvirbius-core/src/sandbox/gvisor_pool.rs:22 · Process kill command — agent can terminate processes//! | with a hard deadline (kill on timeout)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsvirbius-core/tests/e2e_integration.rs:159 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesargs: json!({"path": "/etc/passwd"}),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injection attemptvirbius-core/tests/edge-manifest-debug.json:26 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file"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.
AST01
HIGH
Destructive file system command detectedvirbius-core/src/mcp/pyo3.rs:16 · Destructive file system command detected//! ## Server target formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedvirbius-core/src/mcp/subprocess.rs:7 · Destructive file system command detected//! ## Server target formatFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈60 tok
1 file · 66 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

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. 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.
  2. AWS access key pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. 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.
  6. 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.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim i1see1youPropose a patch to the maintainer