Skills/PyPI/sovereign-mcp

sovereign-mcp@2.0.0

VERIFIED· not started

Publisher claims: "Deterministic MCP Security Architecture. FrozenNamespace as Root of Trust for Model Context Protocol tool verification." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher mattijsmoens · publishing for 243 daysInstalls 148Last detonated 1 h ago
$claude mcp add sovereign-mcp -- uvx sovereign-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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: Verified 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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso openrouter.ai, evil.com — 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
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx sovereign-mcp

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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.1sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.3sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'

Static findings

LOW
Authorization escalation languageAPI_REFERENCE.md:188 · Authorization escalation language · informational: not an instruction file…ection: `"IGNORE ALL PREVIOUS INSTRUCTIONS"`, `"YOU ARE NOW"`, `"ACT AS IF"`, `"DEVELOPER MODE"`, `"JAILBREAK"`, `"SUDO"`, etc. Includes obfuscated variants like `"1GN0R3 PR3…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injection attemptAPI_REFERENCE.md:900 · Prompt injection attempt — model control tokens · informational: not an instruction file- **Step 5: LLM structural token injection** -- Blocks ChatML (`<|im_start|>`), LLaMA (`[INST]`), and Llama2 (`<<SYS>>`) structural tokens used in prompt injection.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
False authorization claimAPI_REFERENCE.md:938 · False authorization claim — impersonating privileged role · informational: not an instruction file- **impersonation** -- i am the admin, override, bypass, emergency, superuser, etc.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Unicode escape sequence detectedsovereign_mcp/input_sanitizer.py:47 · Unicode escape sequence detected — may contain obfuscated payloads_ZERO_WIDTH = re.compile(r"[\u200b\u200c\u200d\u200e\u200f\ufeff\u2060\u2061\u2062\u2063\u2064]")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
LOW
Authorization escalation languageCHANGELOG.md:146 · Authorization escalation language · informational: not an instruction file…tion** — New regex-based layer catches DAN, "Do Anything Now", evil AI persona, developer mode, and content filter bypass patterns. Single-match is sufficient (no 2-hit thres…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
False authorization claimAPI_REFERENCE.md:190 · False authorization claim — impersonating privileged role · informational: not an instruction file2. **Social engineering** (10 patterns) — Authority claims: `"I AM THE ADMIN"`, `"EMERGENCY OVERRIDE"`, `"SAFETY DISABLED"`, `"BYPASS ALL SECURITY"`, `"UNRESTRICTED MODE"`.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Dynamic module loadingsetup.py:39 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
False authorization claimREADME.md:448 · False authorization claim — impersonating privileged role · informational: not an instruction file| **Social Engineering** | `I AM THE ADMIN`, `EMERGENCY OVERRIDE`, `SAFETY DISABLED`, `BYPASS ALL SECURITY` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageREADME.md:278 · Authorization escalation language · informational: not an instruction file…ural constraint enforced by the Python runtime**. There is no API to unlock, no admin override, no escape hatch. The only way to register new tools is to restart the process …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Unicode escape sequence detectedsovereign_mcp/deception_detector.py:27 · Unicode escape sequence detected — may contain obfuscated payloads_ZERO_WIDTH_CHARS = re.compile(r'[\u200b\u200c\u200d\u200e\u200f\ufeff\u2060\u2061\u2062\u2063\u2064]')Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
LOW
Prompt injection attemptREADME.md:431 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file# → (False, [{"category": "injection", "match": "IGNORE ALL PREVIOUS INSTRUCTIONS", ...}])Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptAPI_REFERENCE.md:188 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file…tegories: 1. **Injection phrases** (25 patterns) — Classic prompt injection: `"IGNORE ALL PREVIOUS INSTRUCTIONS"`, `"YOU ARE NOW"`, `"ACT AS IF"`, `"DEVELOPER MODE"`, `"JAILBREAK"`, `"SUDO"`,…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptREADME.md:447 · Prompt injection attempt — model control tokens · informational: not an instruction file| **Injection** | `IGNORE PREVIOUS`, `DISREGARD`, `NEW INSTRUCTIONS`, `[SYSTEM]`, `JAILBREAK`, `DAN MODE` |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionCHANGELOG.md:146 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…ro false positives. #### New Detection Layers - **Layer 5.5: Persona Hijack / Jailbreak Detection** — New regex-based layer catches DAN, "Do Anything Now", evil AI per…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Dynamic module loadingsetup.py:38 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injection attemptREADME.md:521 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file- "IGNORE PREVIOUS INSTRUCTIONS" cannot work because the instructions are frozen and cannot be overriddenFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathssovereign_mcp/permission_checker.py:65 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# e.g. /data/../etc/passwd → /etc/passwd (no longer matches /data/*)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionAPI_REFERENCE.md:190 · Prompt injection — known jailbreak technique reference · informational: not an instruction file2. **Social engineering** (10 patterns) — Authority claims: `"I AM THE ADMIN"`, `"EMERGENCY OVERRIDE"`, `"SAFETY DISABLED"`, `"BYPASS ALL SECURITY"`, `"UNRESTRICTED MODE"`.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:447 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| **Injection** | `IGNORE PREVIOUS`, `DISREGARD`, `NEW INSTRUCTIONS`, `[SYSTEM]`, `JAILBREAK`, `DAN MODE` |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptREADME.md:430 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileDeceptionDetector.scan("IGNORE ALL PREVIOUS INSTRUCTIONS")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packagesovereign_mcp/anti_patterns.py:62 · npx invocation of non-well-known package — may execute untrusted code"reason": "Must pass -y or --yes flag for apt/npm/npx commands",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Leet speak prompt injectionAPI_REFERENCE.md:188 · Leet speak prompt injection — obfuscated 'ignore previous'…LOPER MODE"`, `"JAILBREAK"`, `"SUDO"`, etc. Includes obfuscated variants like `"1GN0R3 PR3V10US"` and spaced-out versions like `"IGN O R E PR E V"`. 2. **Social engineering*…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Prompt injectionAPI_REFERENCE.md:188 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…ection: `"IGNORE ALL PREVIOUS INSTRUCTIONS"`, `"YOU ARE NOW"`, `"ACT AS IF"`, `"DEVELOPER MODE"`, `"JAILBREAK"`, `"SUDO"`, etc. Includes obfuscated variants like `"1GN0R3 PR3…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionAPI_REFERENCE.md:902 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…>`) structural tokens used in prompt injection. - **Step 5.5: Persona hijack / jailbreak detection** -- Single-match regex catches DAN, "Do Anything Now", evil AI perso…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageAPI_REFERENCE.md:902 · Authorization escalation language · informational: not an instruction file…ection** -- Single-match regex catches DAN, "Do Anything Now", evil AI persona, developer mode, and content filter bypass patterns. One match is enough to block. - **Step 6:…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈67 tok
1 file · 51 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

No advisories in OSV for sovereign-mcp@2.0.0 as of 36 min ago. This is the package itself, not its dependencies.