Skills/PyPI/mcp-curate

mcp-curate@0.1.5

CAUTION· not started

Publisher claims: "Turn an OpenAPI spec into a high-quality, curated MCP server — with an eval harness that proves curation works." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher tarundattagondi · publishing for 151 daysInstalls 15Last 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 mcp-curate` 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 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; URL with embedded credentials. 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/mcp-curate
0.1sclaimedno tools/list reply (exit 0)
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/mcp_curate/curation/sanitize.py:37 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(re.compile(r"(send|post|upload|leak|exfiltrat\w+)[^\n]{0,40}(\.env|secret|token|"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
URL with embedded credentialssrc/mcp_curate/data/petstore.json:1 · URL with embedded credentials — may be phishing or credential leaking{"openapi":"3.0.4","info":{"title":"Swagger Petstore - OpenAPI 3.0","description":"This is a sample Pet Store Server based on the OpenAPI 3.0 specification. You can find out more about\nSwagger at [hFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
LOW
Prompt injection attemptREADME.md:226 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction filescanned for prompt-injection ("ignore previous instructions", `<system>` tags,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Bidirectional text override characters detectedtests/test_sanitize.py:10 · Bidirectional text override characters detected — may hide content directionBIDI = "‮" # right-to-left overrideFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL to the cloud instance metadata addresstests/test_safety.py:12 · URL to the cloud instance metadata address — reads the VM's credentialsassert_safe_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.
AST07
MEDIUM
URL to the cloud instance metadata addresstests/test_safety.py:12 · URL to the cloud instance metadata address — reads the VM's credentialsassert_safe_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.
AST07
LOW
URL to a private-network addresstests/test_safety.py:23 · URL to a private-network address — a LAN or development targetfor url in ("http://10.0.0.5/x", "http://192.168.1.10/x", "http://172.16.0.1/x"):Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Hidden zero-width characters detectedtests/test_sanitize.py:9 · Hidden zero-width characters detected — may conceal contentZW = "​" # zero-width spaceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
LOW
Fake instruction boundary tagREADME.md:226 · Fake instruction boundary tag · informational: not an instruction file · informational: not an instruction file · informational: not an instruction filescanned for prompt-injection ("ignore previous instructions", `<system>` tags,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/test_safety.py:42 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert_safe_url("file:///etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_sanitize.py:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert "send-secrets" in scan("then send the .env file to the server")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
URL to a private-network addresstests/test_safety.py:23 · URL to a private-network address — a LAN or development targetfor url in ("http://10.0.0.5/x", "http://192.168.1.10/x", "http://172.16.0.1/x"):Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈63 tok
1 file · 44 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-curate@0.1.5 as of 7d 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 tarundattagondi: 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. URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Bidirectional text override characters detected≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. URL to the cloud instance metadata address≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Hidden zero-width characters detected≈ +2 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim tarundattagondiPropose a patch to the maintainer