testmcpy@0.11.22
CAUTION· install onlyPublisher claims: "A comprehensive testing framework for validating LLM tool calling capabilities with MCP services" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 52 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
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_KEYAUTH_TOKENTESTMCPY_API_KEYTESTMCPY_CHAT_OAUTH_LOGINor--auth-token/--jwt-token/--jwt-secret/--assistant-api-token/--assistant-api-secretConfiguration, not credentials: GITHUB_STEP_SUMMARY, TESTMCPY_ALLOWED_HOSTS, TESTMCPY_CORS_ORIGINS, TESTMCPY_DB_PATH, TESTMCPY_DB_URL, TESTMCPY_SERVER_URL- Where it talks to
- no vendor host named in the codeAlso x.ai, schemastore.org — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names x.ai, schemastore.org as well as its own vendor. The guard injects ANTHROPIC_API_KEY, AUTH_TOKEN, TESTMCPY_API_KEY, TESTMCPY_CHAT_OAUTH_LOGIN only into requests to the host you bind (and its subdomains) and refuses the rest.
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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 75/100 (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; Image alt text carrying instructions; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
# Load environment variables from .env file (for backward compatibility)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Reports — combined view of every test run, evaluator scores, and cost analysisFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.(re.compile(r"(?<![\w.])\.env\b", re.IGNORECASE), ".env file"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# rarely reference SSH keys or /etc/passwd.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."or pass api_key directly."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.path), or the env-format files ``~/.testmcpy`` / ``./.env``.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.load_dotenv(Path(__file__).parent.parent.parent / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# (~/.testmcpy and ./.env). These are the LLM provider API keysFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.(re.compile(r"/etc/passwd\b"), "/etc/passwd"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.(re.compile(r"~?/?\.ssh\b", re.IGNORECASE), "SSH key directory (~/.ssh)"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.3. .env file in current directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# 2. Load from .env in current directory (env-format file)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.cwd_env_file = Path.cwd() / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."SSH keys (~/.ssh, id_rsa), .env files, /etc/passwd — or pair "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# OSError on first-time DB-path init) would otherwise killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for testmcpy@0.11.22 as of 8 h ago. This is the package itself, not its dependencies.
What would make this Verified
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim preset-io: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- 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.
- 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.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.