taiwan-fda-mcp@0.9.0
CAUTION· install onlyPublisher claims: "MCP server exposing Taiwan FDA (TFDA) drug-license and package-insert data to LLM clients. Independent open-source wrapper; not a TFDA product." 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 24 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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso fda.gov.tw, nhi.gov.tw — 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 under the guard. Bundled scripts ran with no arguments; no agent task scenario for this bundle. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
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 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 · 1 s · 2 scenarios · 0 deviationsStatic findings
# brief: Application settings loaded from .env via pydantic-settings.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Application settings — populated from .env / environment variables."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.&& chown -R appuser:appuser /appFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.reader = csv.DictReader(io.StringIO(text.lstrip("")))Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.env_file: .env # operators tune throttle / TTL / volume hereFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Assert the field default directly so a local .env cannot affect the result.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."%E8%A1%9B%E7%BD%B2%E8%97%A5%E8%BC%B8%E5%AD%97%E7%AC%AC021571%E8%99%9F"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.rows_with_bom = parse_rows("" + _FIXTURE.read_text(encoding="utf-8"))Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.RUN mkdir -p /cache && chown appuser:appuser /cacheFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# Assert the field default directly so a local .env cannot affect the result.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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 taiwan-fda-mcp@0.9.0 as of 16 h 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%- Unclaimed publisher≈ +8 on the totalClaim shin13: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Dense URL-encoded content≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.