Skills/PyPI/mcp-defense

mcp-defense@0.1.2

CAUTION· static only

Publisher claims: "Kernel-native runtime defense for AI agents. MCP tool-call policy + kernel correlation for Claude Code, Codex, Devin, and other agentic workloads." Observed in sandbox: static analysis only — behavior not yet observed.

Registry PyPI (MCP server)Publisher jessfortemnaturae8717 · publishing for 204 daysInstalls 16Last detonated 7d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Before you give it your token

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
nothing has run yet
What we could not test
everything: the server has not run yet

Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.

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 analysed it statically (a sandbox run is pending) on 2026-11-07 and scored it 63/100 (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: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Access to sensitive file pathssrc/mcp_defense/policy/approval.py:4 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfile like `/workspace/.env.local`), an InteractiveApprovalGate pauses andFix: 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_defense/policy/crown_jewels.py:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescrown jewels (/etc/shadow) in that it emphasizes what a prompt-injected AIFix: 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_defense/policy/matcher.py:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`/workspace/**/.env.local`. Hand-rolled to avoid an extra dependency.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive file system command detectedDockerfile:32 · Destructive file system command detectedrm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_flight_recorder.py:124 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filestool_call=_tool_call(tool_args={"path": "/workspace/.env.local"}),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
URL to a private-network addresstests/test_extractor.py:25 · URL to a private-network address — a LAN or development targetassert extract_urls({"endpoint": "http://10.0.0.1"}) == ["http://10.0.0.1"]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Access to sensitive file pathstests/test_approval.py:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreason="sensitive path: /workspace/.env.local",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_defense/policy/crown_jewels.py:93 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/workspace/.env": Sensitivity.AUTH,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_defense/policy/crown_jewels.py:94 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/workspace/**/.env.local": Sensitivity.AUTH,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_matcher.py:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert not path_matches("/etc/hosts", "/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_defense/policy/crown_jewels.py:71 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/Users/*/.netrc": Sensitivity.AUTH,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive file system command detectedDockerfile:42 · Destructive file system command detectedrm /tmp/mcp_defense-*.whlFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
URL to a private-network addresstests/test_extractor.py:25 · URL to a private-network address — a LAN or development targetassert extract_urls({"endpoint": "http://10.0.0.1"}) == ["http://10.0.0.1"]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathssrc/mcp_defense/policy/crown_jewels.py:70 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/home/*/.netrc": Sensitivity.AUTH,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_approval.py:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filestool_args=args or {"path": "/workspace/.env.local"},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_policy_engine.py:93 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files_event("filesystem", "read_file", {"path": "/workspace/app/.env.local"})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_matcher.py:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert path_matches("/workspace/**/.env.local", "/workspace/a/b/c/.env.local")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_matcher.py:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert path_matches("/workspace/**/.env.local", "/workspace/.env.local")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_smoke.py:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert classify_path("/workspace/app/.env.local") == Sensitivity.AUTHFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈72 tok
1 file · 59 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for mcp-defense@0.1.2 as of 7d ago. This is the package itself, not its dependencies.

What would make this Verified

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jessfortemnaturae8717: 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. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. URL to a private-network address≈ +1 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jessfortemnaturae8717Propose a patch to the maintainer