Skills/PyPI/mcpmap

mcpmap@1.0.0

CAUTION· not started

Publisher claims: "Static attack surface analyzer for AI agents, MCP servers, and LLM tool definitions." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher bogdanticu88 · publishing for 183 daysInstalls 8Last 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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso owasp.org, mitre.org, shields.io, githubusercontent.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 mcpmap

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 79/100 (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; Access to sensitive file paths. 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 injection attemptmcpmap/mcpmap_rules.yaml:877 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file- "ignore previous instructions"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptmcpmap/mcpmap_rules.yaml:896 · Prompt injection attempt — model control tokens · informational: not an instruction file- "[INST]"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptmcpmap/mcpmap_rules.yaml:879 · Prompt injection attempt — 'disregard previous' · informational: not an instruction file- "disregard previous"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionmcpmap/mcpmap_rules.yaml:869 · Prompt injection — known jailbreak technique reference · informational: not an instruction filename: "LLM Jailbreak"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionmcpmap/mcpmap_rules.yaml:892 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- "DAN mode"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commandmcpmap/mcpmap_rules.yaml:228 · Process kill command — agent can terminate processes- kill processFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsmcpmap/mcpmap_rules.yaml:718 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- "/etc/passwd"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_engine.py:173 · MCP server using network transport (SSE/HTTP) — data sent over networkdata = {"mcpServers": {"remote": {"url": "https://mcp.example.com/sse", "env": {}}}}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actiontests/test_cli.py:297 · File type combined with upload action — agent may exfiltrate local data filesassert "claude_desktop_config.json" in result.outputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionmcpmap/cli.py:112 · File type combined with upload action — agent may exfiltrate local data files" mcpmap scan config.json --format html --output report.html\n\n"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Authorization escalation languagemcpmap/mcpmap_rules.yaml:893 · Authorization escalation language · informational: not an instruction file- "developer mode"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionmcpmap/cli.py:322 · File type combined with upload action — agent may exfiltrate local data filesif format in (OutputFormat.markdown, OutputFormat.json, OutputFormat.sarif):Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsmcpmap/mcpmap_rules.yaml:715 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- ".netrc"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionmcpmap/mcpmap_rules.yaml:891 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- "jailbreak"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionmcpmap/mcpmap_rules.yaml:673 · Prompt injection — known jailbreak technique reference · informational: not an instruction filename: "LLM Jailbreak"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionmcpmap/mcpmap_rules.yaml:893 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- "developer mode"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptmcpmap/mcpmap_rules.yaml:888 · Prompt injection attempt — explicit instruction override · informational: not an instruction file- "override your instructions"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionmcpmap/cli.py:110 · File type combined with upload action — agent may exfiltrate local data files" mcpmap scan config.json --format sarif --output results.sarif\n\n"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Fake instruction boundary tagmcpmap/mcpmap_rules.yaml:895 · Fake instruction boundary tag · informational: not an instruction file- "<system>"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagemcpmap/engine.py:341 · npx invocation of non-well-known package — may execute untrusted codepkg_match = re.search(r"'npx -y ([^']+)'", evidence) or \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionREADME.md:534 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- **[MITRE ATLAS](https://atlas.mitre.org/)**: AML.T0051.000 (Direct Prompt Injection), AML.T0051.001 (Indirect Prompt Injection), AML.T0054 (LLM Jailbreak), AML.T0048 (Societal Harm)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsmcpmap/mcpmap_rules.yaml:701 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexplicit deny rules for ~/.ssh, ~/.gnupg, ~/.aws, browser profileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈54 tok
1 file · 37 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 mcpmap@1.0.0 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim bogdanticu88: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. 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.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim bogdanticu88Propose a patch to the maintainer