syia-mcp-survey-2025-x7k9@0.1.17
CAUTION· install onlyPublisher claims: "MCP Survey Module" 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 48 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
LLAMA_API_KEYOPENAI_API_KEYPERPLEXITY_API_KEYTYPESENSE_API_KEYor--llama-api-key/--typesense-api-key/--openai-api-key/--perplexity-api-keyConfiguration, not credentials: MONGODB_DB_NAME, MONGODB_URI, TYPESENSE_HOST, TYPESENSE_PORT, TYPESENSE_PROTOCOL, VENDOR_MODEL- Where it talks to
- no vendor host named in the codeAlso syia.ai, siya.com, llamaindex.ai, google.com, qtweb.net, bing.com, amazonaws.com, perplexity.ai, ccs-service.net, or.jp, krs.co.kr, veracity.com, dnv.com, lr.org, bureauveritas.com, eagle.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 syia.ai, siya.com, llamaindex.ai, google.com, qtweb.net, bing.com, amazonaws.com, perplexity.ai, ccs-service.net, or.jp, krs.co.kr, veracity.com, dnv.com, lr.org, bureauveritas.com, eagle.org as well as its own vendor. The guard injects LLAMA_API_KEY, OPENAI_API_KEY, PERPLEXITY_API_KEY, TYPESENSE_API_KEY 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 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials; Access to sensitive file paths; Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
await page1.get_by_role('textbox', name='Enter your password').fill(uid_password)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.print("Set it in your environment, in a .env file, or provide it with --llama-api-key.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.await page1.get_by_role('textbox', name='Enter your password').click()Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.cron = eval(job["cron"]) if isinstance(job["cron"], str) else job["cron"]Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.from .credentials import ABS_CREDENTIALS, BV_CREDENTIALS, LR_CREDENTIALS, DNV_CREDENTIALS, KR_CREDENTIALS, NK_CREDENTIALS, CCS_CREDENTIALSFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."rm -rf /*",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."rm -rf /*",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.print("Set it in your environment, in a .env file, or provide it with --llama-api-key.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."chmod -R 777 /",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.[mcp_server.vessel_search]Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."chown -R",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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 syia-mcp-survey-2025-x7k9@0.1.17 as of 18 h ago. This is the package itself, not its dependencies.
What would make this Verified
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim syia-ai: 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.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.