Skills/PyPI/mcp-bastion-python

mcp-bastion-python@5.1.0

CAUTION· not started

Publisher claims: "Security middleware for MCP servers protecting LLM agents from prompt injection, resource exhaustion, and PII leakage" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher vaquarkhan · publishing for 265 daysInstalls 664Last detonated 8d ago
What would fix thisWatchDispute verdict

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

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
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try mcp-bastion-python` runs it now and prints the full answer.

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; not started: dependency install failed; the server itself was not observed) on 2026-11-06 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: Auto-update or dynamic fetch configuration; Auto-update or dynamic fetch configuration; Auto-update or dynamic fetch configuration. 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
0.1sprocessdependency install exit 1
0.1sprocessexec /usr/bin/date
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/mcp-bastion
0.1sclaimedno tools/list reply (exit 0)
0.1sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Auto-update or dynamic fetch configurationsrc/mcp_bastion/config.py:188 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload_poll_seconds: float = 2.0Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_bastion/config.py:575 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload=bool(hot_reload.get("enabled", False)),Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_bastion/config.py:576 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload_poll_seconds=float(hot_reload.get("poll_seconds", 2.0)),Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_bastion/issue_guides.py:387 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"fix": ["Use a secrets manager adapter; avoid .env in production images."],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_bastion/pillars/content_filter.py:44 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# N-3: secret .env files — not devops talk about templates/examples (I-23 FP).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_bastion/config.py:1361 · Auto-update or dynamic fetch configuration — agent may load new code at runtimepoll_seconds=config.hot_reload_poll_seconds,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcp_bastion/cli.py:137 · Python subprocess execution detectedreturn subprocess.run(argv, env=env).returncodeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_bastion/doctor.py:488 · Python subprocess execution detectedproc = subprocess.run(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_bastion/skill_scan.py:181 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesmessage="Skill body references credential path (@.env / @~/.aws / @~/.ssh)",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_bastion/pillars/external_policy.py:268 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, text=True, timeout=8)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_bastion/config.py:1357 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeif config.hot_reload and path is not None and path.exists():Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)src/mcp_bastion/cli.py:39 · MCP server using network transport (SSE/HTTP) — data sent over network{"mcpServers": {"mcp-bastion": {"url": f"http://{client_host}:{port}"}}},Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Access to sensitive file pathssrc/mcp_bastion/pillars/content_filter.py:45 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr"(?i)(?:^|[\s\"'=])\.env(?:\.local)?(?!\.(?:example|sample|template|dist|defaults?))"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_bastion/skill_scan.py:23 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr"@[~/][\w./\\-]*(\.env|\.aws[/\\]credentials|\.ssh[/\\]|id_rsa|id_ed25519)",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_bastion/pillars/external_policy.py:112 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
AWS access key pattern detectedsrc/mcp_bastion/redteam.py:122 · AWS access key pattern detected — possible hardcoded or harvested keyarguments={"prompt": "Use this AWS key AKIAIOSFODNN7EXAMPLE in production"},Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Access to sensitive file pathssrc/mcp_bastion/redteam.py:98 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesarguments={"path": "../../etc/passwd"},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_bastion/risk_audit.py:268 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files_scan_mapping_for_secrets(env, path=path, prefix=f"{name}.env", findings=findings)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injection attemptREADME.md:911 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file1. **Regex heuristics** (always on) block obvious jailbreak strings such as “ignore previous instructions” - no model download required.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:911 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file1. **Regex heuristics** (always on) block obvious jailbreak strings such as “ignore previous instructions” - no model download required.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:581 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file| **Prompt injection defense** | Meta **PromptGuard** scores tool arguments; malicious / jailbreak-style payloads can be blocked before execution (local inference, no third-party API). |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:503 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file- **Prompt injection defense:** Heuristic jailbreak blocking out of the box; Meta PromptGuard ML when Hugging Face access is configured.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptREADME.md:1410 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file2. Call a tool with "Ignore previous instructions" (should be blocked)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:1309 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file| -32001 | `PromptInjectionError` | Tool args contain jailbreak/injection |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:506 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file- **Response scan:** Blocks jailbreak patterns in outbound tool/resource text.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈69 tok
1 file · 81 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 mcp-bastion-python@5.1.0 as of 10 h ago. This is the package itself, not its dependencies.

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 vaquarkhan: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  3. 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.
  4. AWS access key pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  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. 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.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim vaquarkhanPropose a patch to the maintainer