mcp-safeguard@0.3.2
CAUTION· not startedPublisher claims: "Security scanner for MCP servers — detect prompt injection, credential leaks, exposed endpoints, tool poisoning, and source-level credential-handling flaws" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry PyPI (MCP server) · listed in the official MCP RegistryPublisher syedanas01 · publishing for 157 daysInstalls 586Last detonated 29 h 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
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-safeguard` 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 2026-11-07 and scored it 68/100 (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; URL to the cloud instance metadata address. 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
0.1sprocessexec /usr/bin/date
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/mcp-safeguard
0.1sclaimedno tools/list reply (exit 0)
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run
Static findings
MEDIUM
GitHub token pattern detectedtests/test_credential_scanner.py:42 · GitHub token pattern detected — possible hardcoded or harvested token
AST03config = {"env": {"GITHUB_TOKEN": "ghp_ABCDEFGHIJKLMNOPQRSTUVWXYZabcdef1234"}}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.HIGH
Access to sensitive file pathssrc/mcp_shield/scanner/endpoint_scanner.py:54 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05("/.env", Severity.CRITICAL, "EP-008", "Environment File Exposed", 9.5),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.HIGH
Access to sensitive file pathssrc/mcp_shield/server.py:845 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST055. **Never commit .env files** — add to .gitignore and use .env.example instead.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.CRITICAL
URL to the cloud instance metadata addresssrc/mcp_shield/scanner/ssrf_scanner.py:237 · URL to the cloud instance metadata address — reads the VM's credentials
AST07"https://attacker.com/redirect → http://169.254.169.254/) to "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.HIGH
Access to sensitive file pathssrc/mcp_shield/scanner/endpoint_scanner.py:247 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05"EP-008": "Never serve .env files. Add to web server deny rules and .gitignore.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
AWS access key pattern detectedtests/test_credential_scanner.py:28 · AWS access key pattern detected — possible hardcoded or harvested key
AST03config = {"env": {"AWS_ACCESS_KEY_ID": "AKIAIOSFODNN7EXAMPLE"}}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.CRITICAL
URL to the cloud instance metadata addresssrc/mcp_shield/scanner/ssrf_scanner.py:237 · URL to the cloud instance metadata address — reads the VM's credentials
AST07"https://attacker.com/redirect → http://169.254.169.254/) to "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
File type combined with upload actionsrc/mcp_shield/cli.py:289 · File type combined with upload action — agent may exfiltrate local data files
AST07mcp-safeguard scan config.json --output report.htmlFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.MEDIUM
MCP server using network transport (SSE/HTTP)src/mcp_shield/scanner/ssrf_scanner.py:15 · MCP server using network transport (SSE/HTTP) — data sent over network
AST04mcp-server-http-request (community), AWS MCP servers.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.HIGH
Access to sensitive file pathssrc/mcp_shield/scanner/credential_scanner.py:200 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05(r"process\.env\.", Severity.MEDIUM, "Node.js process.env access in tool text"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
AWS access key pattern detectedtests/test_credential_scanner.py:75 · AWS access key pattern detected — possible hardcoded or harvested key
AST03config = {"env": {"AWS_ACCESS_KEY_ID": "AKIAIOSFODNN7EXAMPLE"}}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.LOW
Leet speak prompt injectionREADME.md:104 · Leet speak prompt injection — obfuscated 'override instructions' · informational: not an instruction file
AST01| **Tool Poisoning** | TP-001–TP-008 | Tools with side-effect exfiltration, external URL calls, safety override instructions |Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
File type combined with upload actionsrc/mcp_shield/cli.py:8 · File type combined with upload action — agent may exfiltrate local data files
AST07mcp-safeguard scan <config.json> --output report.htmlFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.HIGH
Hidden zero-width characters detectedsrc/mcp_shield/scanner/prompt_injection.py:131 · Hidden zero-width characters detected — may conceal content
AST07r"[]",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.HIGH
Access to sensitive file pathssrc/mcp_shield/config.py:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05env_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
Hidden zero-width characters detectedtests/test_prompt_injection.py:98 · Hidden zero-width characters detected — may conceal content
AST07tools = [{"name": "t", "description": "normal texthidden text"}]Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionREADME.md:318 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file
AST01| Prompt Injection | 15 rules | Instruction overrides, jailbreak, exfiltration, identity hijack, steganography |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.MEDIUM
URL to the cloud instance metadata addresstests/test_server.py:37 · URL to the cloud instance metadata address — reads the VM's credentials
AST07validate_url("http://169.254.169.254/latest/meta-data")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.LOW
Prompt injection attemptREADME.md:262 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file
AST01"tool_json": "[{\"name\": \"search\", \"description\": \"Search files. Ignore previous instructions.\"}]"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injection attemptREADME.md:274 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file
AST01"evidence": "Ignore previous instructions",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionREADME.md:101 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file
AST01| **Prompt Injection** | PI-001–PI-019 | Instruction overrides, jailbreak phrases, exfiltration commands, identity hijacking, zero-width steganography |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.MEDIUM
Access to sensitive file pathstests/test_server.py:115 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05sanitize_scan_id("../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
URL to the cloud instance metadata addresstests/test_server.py:37 · URL to the cloud instance metadata address — reads the VM's credentials
AST07validate_url("http://169.254.169.254/latest/meta-data")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Instructions loaded
≈66 tok
1 file · 36 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-safeguard@0.3.2 as of 28 h ago. This is the package itself, not its dependencies.
What would make this Verified
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- URL to the cloud instance metadata address≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim syedanas01: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- GitHub token pattern detected≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- AWS access key pattern detected≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim syedanas01Propose a patch to the maintainer