ripple-mcp@0.6.0
CAUTION· static onlyPublisher claims: "Self-hosted codebase intelligence platform — graph + vector indexing with MCP tools for IDE-embedded LLMs" Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Before you give it your token
- It will ask for
COHERE_API_KEYHRCODE_MEM_TOKEN_THRESHOLDHRCODE_TOKEN_COMPACTHRCODE_TOKEN_WARNJINA_API_KEYKIMI_API_KEYLLM_API_KEYOPENAI_API_KEYVOYAGE_API_KEYConfiguration, not credentials: ARTIFACT_DIR, CALL_DELAY, CONFIG_PATH, EMBED_BATCH_SIZE, EMBED_MODEL, EMBED_PROVIDER, EMBED_PROVIDER_MODEL, EMBED_SERVER_HOST, EMBED_SERVER_PORT, EMBED_SERVER_URL, GIT_HISTORY, GUARDRAIL_TOP_N, HR_ARTIFACT_DIR, HR_CHAT_AUTO_SURFACE_GUARDRAILS, HR_CRIT_ALPHA, HR_CRITICALITY_BOOST, HR_GUARD_DISABLE, HR_GUARD_PATH, HR_LIGHTWEIGHT_MODE, HR_RERANKER, HR_RERANKER_ALPHA, HR_RERANKER_MODEL, HR_RERANKER_TOPK, HRCODE_BASH_TIMEOUT, HRCODE_COMPACT_KEEP, HRCODE_CONFIG, HRCODE_CWD, HRCODE_MAX_HISTORY, HRCODE_MAX_OUTPUT, HRCODE_MAX_READ_BYTES, HRCODE_MAX_READ_LINES- Where it talks to
- no vendor host named in the codeAlso juspay.net, jina.ai — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- nothing has run yet
- What we could not test
- everything: the server has not run yet
Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.
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 analysed it statically (a sandbox run is pending) on 2026-11-16 and scored it 52/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: URL with embedded credentials; URL with embedded credentials; URL with embedded credentials. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
"https://fonts.googleapis.com/css2?family=JetBrains+Mono:ital,wght@0,400;0,500;1,400&display=swap"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.… } } }, "auth": { "login": { "title": "\u0a8f\u0aaa\u0acd\u0ab2\u0abf\u0a95\u0ac7\u0ab6\u0aa8 \u0a8d\u0a95\u0acd\u0ab8\u0ac7\u0ab8 \u0a95\u0ab0\u0ab5\u0abe \u0aae\u0abe\u0a9…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."confirm": "\u092a\u0941\u0937\u094d\u091f\u093f \u0915\u0930\u0947\u0902",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."confirm": "\u0aaa\u0ac1\u0ab7\u0acd\u0a9f\u0abf \u0a95\u0ab0\u0acb",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."default": "\u098f\u0995\u099f\u09bf \u09a4\u09cd\u09b0\u09c1\u099f\u09bf \u0998\u099f\u09c7\u099b\u09c7",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."default": "\u30a8\u30e9\u30fc\u304c\u767a\u751f\u3057\u307e\u3057\u305f",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."default": "\u090f\u0915 \u0924\u094d\u0930\u0941\u091f\u093f \u0939\u0941\u0908",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."serverConnection": "\u0938\u0930\u094d\u0935\u0930 \u0938\u0947 \u0938\u0902\u092a\u0930\u094d\u0915 \u0928\u0939\u0940\u0902 \u0939\u094b \u092a\u093e \u0930\u0939\u093e"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600&display=swap');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."serverConnection": "\u30b5\u30fc\u30d0\u30fc\u306b\u63a5\u7d9a\u3067\u304d\u307e\u305b\u3093\u3067\u3057\u305f"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."loading": "\u0ab2\u0acb\u0aa1 \u0aa5\u0a88 \u0ab0\u0ab9\u0acd\u0aaf\u0ac1\u0a82 \u0a9b\u0ac7...",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.@import url('https://fonts.googleapis.com/css2?family=JetBrains+Mono:ital,wght@0,400;0,500;1,400&display=swap');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."serverConnection": "\u0ab8\u0ab0\u0acd\u0ab5\u0ab0 \u0ab8\u0ac1\u0aa7\u0ac0 \u0aaa\u0ab9\u0acb\u0a82\u0a9a\u0ac0 \u0ab6\u0a95\u0abe\u0aaf\u0ac1\u0a82 \u0aa8\u0aa5\u0ac0"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…99f\u09bf \u0998\u099f\u09c7\u099b\u09c7", "serverConnection": "\u09b8\u09be\u09b0\u09cd\u09ad\u09be\u09b0\u09c7\u09b0 \u09b8\u09be\u09a5\u09c7 \u09b8\u0982\u09af\u09cb\u0997 \u0995\u09b0\u09be \u09…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."required": "\u0908\u092e\u0947\u0932 \u090f\u0915 \u0906\u0935\u0936\u094d\u092f\u0915 \u092b\u093c\u0940\u0932\u094d\u0921 \u0939\u0948",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."confirm": "\u09a8\u09bf\u09b6\u09cd\u099a\u09bf\u09a4 \u0995\u09b0\u09c1\u09a8",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.IDE config: {"url": "https://<tunnel>.trycloudflare.com/sse"}Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."title": "\u30a2\u30d7\u30ea\u306b\u30ed\u30b0\u30a4\u30f3",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."continue": "\u099a\u09be\u09b2\u09bf\u09af\u09bc\u09c7 \u09af\u09be\u09a8",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.python3 mcp_server.py --http [--port 8002]Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.("chmod 777 recursive", re.compile(r"\bchmod\b.*-R.*777\b", re.I)),Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.proc = subprocess.run(["python3", "-c", script], capture_output=True, text=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."required": "\u30e1\u30fc\u30eb\u30a2\u30c9\u30ec\u30b9\u306f\u5fc5\u9808\u9805\u76ee\u3067\u3059",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.result = subprocess.run("fuser -k 8002/tcp", shell=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.if subprocess.run(f"which {tool}", shell=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."default": os.environ.get("MCP_SERVER_URL", "http://localhost:8002"),Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.BASE_URL = os.environ.get("LLM_BASE_URL", "http://172.19.144.1:1234/v1")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.found = subprocess.run(f"which {tool}", shell=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.notes_cp = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.head_cp = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(args, capture_output=True, text=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.("kill all processes", re.compile(r"\bkillall\b|\bkill\s+-9\s+-1\b")),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."label": "\u30e1\u30fc\u30eb\u30a2\u30c9\u30ec\u30b9",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.subprocess.run(["git", "clone", "--depth=500", url, target],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.BASE_URL = os.environ.get("LLM_BASE_URL", "http://172.19.144.1:1234/v1")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(["git", "rev-list", "--count", "HEAD"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(["node", "-e", script], capture_output=True, text=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# 1. graph_with_summaries.json — copy from output→artifact if artifact is stale/missingFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."[mcp_server] Start embed_server.py and set EMBED_SERVER_URL=http://localhost:8001\n"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.print(f"[mcp_server] Starting HTTP/SSE server on http://127.0.0.1:{MCP_PORT}/sse", file=sys.stderr)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."hypercode": os.environ.get("MCP_SERVER_URL", "http://localhost:8002"),Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.log = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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 ripple-mcp@0.6.0 as of 6 min ago. This is the package itself, not its dependencies.
What would make this Verified
28 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim amitshukla2308: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- Tunneling service URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.