mcp-bandit@0.1.1
VERIFIED· not startedPublisher claims: "Security scanner for Model Context Protocol (MCP) servers" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry PyPI (MCP server)Publisher giridharpandurangi · publishing for 191 daysInstalls 12Last detonated 8d 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: 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
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-bandit` 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 81/100 (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 · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1
0.2sprocessexec /usr/bin/date
0.2sprocessexec /usr/bin/timeout
0.2sprocessexec .venv/bin/mcp-bandit
0.2sclaimedno tools/list reply (exit 0)
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run
Static findings
MEDIUM
Python subprocess execution detectedtests/test_rules_ssrf.py:383 · Python subprocess execution detected
AST05subprocess.run(cmd, shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/test_ssrf_property.py:171 · Python subprocess execution detected
AST05result = subprocess.run("ls -la", shell=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtest-mcp-bandit/Scripts/pywin32_testall.py:25 · Python subprocess execution detected
AST05result = subprocess.run(cmd, check=False, cwd=dirname)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/fixtures/ssrf/mcp004_positive.py:8 · Python subprocess execution detected
AST05return subprocess.run(cmd, shell=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.CRITICAL
URL to the cloud instance metadata addressmcp_scan/dynamic/probes.py:6 · URL to the cloud instance metadata address — reads the VM's credentials
AST07"http://169.254.169.254/latest/meta-data/", # AWS metadataFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
Python subprocess execution detectedtests/test_ssrf_property.py:235 · Python subprocess execution detected
AST05result = subprocess.run(["echo", name], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/test_rules_ssrf.py:334 · Python subprocess execution detected
AST05subprocess.call(cmd, shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/test_ssrf_property.py:162 · Python subprocess execution detected
AST05result = subprocess.run(["ls", "-la"], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/fixtures/ssrf/mcp004_negative.py:8 · Python subprocess execution detected
AST05return subprocess.run(["ls", "-la"], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/test_rules_ssrf.py:360 · Python subprocess execution detected
AST05subprocess.run(cmd, shell=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.CRITICAL
URL to the cloud instance metadata addressmcp_scan/dynamic/probes.py:6 · URL to the cloud instance metadata address — reads the VM's credentials
AST07"http://169.254.169.254/latest/meta-data/", # AWS metadataFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
Python subprocess execution detectedtests/test_rules_ssrf.py:347 · Python subprocess execution detected
AST05subprocess.Popen(cmd, shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/test_rules_ssrf.py:372 · Python subprocess execution detected
AST05subprocess.run("ls -la", shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/test_ssrf_property.py:212 · Python subprocess execution detected
AST05subprocess.run(cmd, shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/test_models_property.py:125 · Python subprocess execution detected
AST05"subprocess.run({var}, shell=True)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/test_ssrf_property.py:331 · Python subprocess execution detected
AST05f" result = subprocess.run({cmd}, shell=True, capture_output=True)\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.LOW
Prompt injection attempttests/snapshots/sarif_with_findings.json:41 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file
AST01"text": "Tool description contains prompt injection phrase: ignore previous instructions"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injection attempttests/snapshots/markdown_with_findings.md:36 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file
AST01**Message:** Tool description contains prompt injection phrase: ignore previous instructionsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injection attempttests/snapshots/markdown_with_findings.md:14 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file
AST01| MCP021 | HIGH | `src/server.py:5` | Tool description contains prompt injection phrase: ignore previous instructions |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injection attempttests/snapshots/sarif_with_findings.json:96 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file
AST01"text": "Tool description contains prompt injection phrase: ignore previous instructions"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.MEDIUM
Python subprocess execution detectedtests/test_static_analyzer_property.py:56 · Python subprocess execution detected
AST05"import subprocess\n\[email protected]()\ndef run_cmd(cmd):\n return subprocess.run(cmd, shell=True)\n",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.LOW
Prompt injection attempttests/snapshots/json_with_findings.json:26 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file
AST01"message": "Tool description contains prompt injection phrase: ignore previous instructions",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injection attempttests/snapshots/rich_with_findings.txt:9 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file
AST01│ │ │ │ ignore previous instructions │Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Instructions loaded
≈50 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-bandit@0.1.1 as of 7d ago. This is the package itself, not its dependencies.