Skills/PyPI/mcp-behave

mcp-behave@0.4.5

CAUTION· not started

Publisher claims: "Runtime behavioral auditor for MCP servers — scope-violation detection via native libc interposition & runtime tracing" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher navid72m · publishing for 149 daysInstalls 354Last detonated 24 min ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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
MCP_BEHAVE_TOKENConfiguration, not credentials: MCP_BEHAVE_ALLOW_ALL_EXEC, MCP_BEHAVE_ALLOWED_COMMANDS, MCP_BEHAVE_CALL_TIMEOUT, MCP_BEHAVE_DASHBOARD_URL, MCP_BEHAVE_DEBUG, MCP_BEHAVE_EBPF_REQUIRED, MCP_BEHAVE_MOCK_EBPF, MCP_BEHAVE_STATE_DIR, MCP_BEHAVE_UNSAFE_HOST, OUT_DIR, PROBE_NOISE_EXTRA, TRACE_FILE, XDG_STATE_HOME
Where it talks to
mcp-behave.dev (its own)Also githubusercontent.com, example.org, example.net, modelcontextprotocol-security.io — 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
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names githubusercontent.com, example.org, example.net, modelcontextprotocol-security.io as well as its own vendor. The guard injects MCP_BEHAVE_TOKEN only into requests to mcp-behave.dev (and its subdomains) and refuses the rest.

$vet-skills run --secrets MCP_BEHAVE_TOKEN=mcp-behave.dev -- uvx mcp-behave

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 0.3.0

vet-skills diff mcp-behave 0.3.0 0.4.5

This version reaches for something 0.3.0 did not: 3 new hosts (example.net, example.org, mcp-behave.dev) · 2 new credential files (~/.ssh/config, ~/.ssh/known_hosts). Compared from the two recorded runs, not from source.

New hosts
example.net, example.org, mcp-behave.dev
New credential files
~/.ssh/config, ~/.ssh/known_hosts
No longer contacted
astral.sh, attacker-c2.example, python.org

0.4.5 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.3sprocessdependency install exit 1 ·
0.3sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/mcp_behave/analyze.py:45 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn True, "/etc/shadow"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/analyze.py:56 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif ".netrc" in parts:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/lint.py:113 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env", "id_rsa", "id_ed25519", ".ssh", ".pem", ".key", "private_key",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/analyze.py:44 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif norm == "/etc/shadow" or norm.endswith("/etc/shadow"):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
AWS access key pattern detectedsrc/mcp_behave/probe.py:71 · AWS access key pattern detected — possible hardcoded or harvested keyf.write("[default]\naws_access_key_id = AKIAIOSFODNN7EXAMPLE\naws_secret_access_key = wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY\n")Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Access to sensitive file pathssrc/mcp_behave/probe.py:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(.ssh/id_rsa, .aws/credentials, .env, .netrc) so credential probes trip detectionFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/analyze.py:57 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn True, ".netrc"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/config_scanner.py:245 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileselif any(sens in arg_norm for sens in ("/.ssh", "/.aws", "/.kube", "/.gnupg", "/etc/shadow")):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/lint.py:114 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".aws", ".kube", "/etc/passwd", "/etc/shadow", ".npmrc", ".git/config",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandsrc/mcp_behave/cli.py:29 · Privileged sudo command — agent may execute with elevated privilegesthe server. This runs as YOU -- no sudo needed. Two things can prevent it:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_behave/protocol.py:189 · Python subprocess execution detectedsubprocess.Popen(["osascript", "-e", script], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injection attemptREADME.md:527 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file[!] HIGH prompt injection pattern detected in tool 'notes_analyzer' description: 'Ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathssrc/mcp_behave/report.py:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesSENSITIVE = (".ssh", "id_rsa", "id_ed25519", ".env", ".aws", "credentials",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_behave/wrap.py:44 · Python subprocess execution detectedsubprocess.Popen(["osascript", "-e", script], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/probe.py:73 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileswith open(os.path.join(canary_dir, ".env"), "w") as f:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_behave/sandbox.py:26 · Python subprocess execution detectedres = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/mcp_behave/identity.py:256 · npx invocation of non-well-known package — may execute untrusted code# 1. NPX / Node.jsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_behave/report.py:384 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdeclared_paths.add(os.path.expanduser("~/.ssh/config"))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/probe.py:76 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileswith open(os.path.join(canary_dir, ".netrc"), "w") as f:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/probe.py:517 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("../../../../../../../../etc/passwd", -1),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_behave/report.py:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".netrc", "/etc/shadow", ".kube", ".docker/config")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/mcp_behave/cli.py:162 · MCP server using network transport (SSE/HTTP) — data sent over network"`python -m mcp_server_fetch`). For --transport sse/"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagesrc/mcp_behave/config_scanner.py:10 · npx invocation of non-well-known package — may execute untrusted code- Unpinned remote package execution (e.g. npx without version tag).Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injection attemptREADME.md:503 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file- Direct prompt injection patterns (e.g., `Ignore previous instructions`, `SYSTEM PROMPT:`, `<system>`, `[system instruction]`, `you must always call this tool first`).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedsrc/mcp_behave/probe.py:215 · Python subprocess execution detectedsubprocess.run([cc, "-shared", "-fPIC", "-O2", "-o", so, src, "-ldl"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_behave/probe.py:182 · Python subprocess execution detectedout = subprocess.run([cs, "-d", "--verbose=4", path],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_behave/probe.py:156 · Python subprocess execution detectedsubprocess.run([cc, *arch_flags, "-dynamiclib", "-O2",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_behave/identity.py:116 · Python subprocess execution detectedres = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/mcp_behave/identity.py:77 · npx invocation of non-well-known package — may execute untrusted code"""Inspect local NPX runner arguments and local disk cache offline (or query registry if allow_network=True)."""Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_behave/report.py:385 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdeclared_paths.add(os.path.expanduser("~/.ssh/known_hosts"))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Fake instruction boundary tagREADME.md:503 · Fake instruction boundary tag · informational: not an instruction file- Direct prompt injection patterns (e.g., `Ignore previous instructions`, `SYSTEM PROMPT:`, `<system>`, `[system instruction]`, `you must always call this tool first`).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionsrc/mcp_behave/lint.py:514 · File type combined with upload action — agent may exfiltrate local data fileshelp="Path to manifest.json, tools.json, output directory, or '-' for stdin (default: stdin).",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈65 tok
1 file · 34 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim navid72m: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. AWS access key pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  4. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim navid72mPropose a patch to the maintainer