oracle.data-studio-mcp-server@2.0.0
CAUTION· install onlyPublisher claims: "Oracle Data Studio MCP server — Essbase, ADP (Autonomous Database Data Platform), and Data Transforms with Oracle 23ai annotation-aware query routing" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- 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
ADP_PASSWORDDT_PASSWORDESSBASE_PASSWORDESSBASE_TOKENMCP_AUTH_TOKENor--auth-token/--essbase-password/--essbase-token/--adp-password/--dt-passwordConfiguration, not credentials: MCP_ALLOW_INSECURE_BIND- Where it talks to
- no vendor host named in the codeAlso oracle.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- 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 oracle.com as well as its own vendor. The guard injects ADP_PASSWORD, DT_PASSWORD, ESSBASE_PASSWORD, ESSBASE_TOKEN, MCP_AUTH_TOKEN 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-14 and scored it 77/100 (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; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
# kill requires confirm=session_id (LLM06 mitigation)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.message — e.g. "delete application", "kill session".Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.confirm: Confirmation token (required for kill and kill_all).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.from oracle.data_studio_mcp_server.http_runtime import is_loopbackFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.'essbase_manage_sessions', # can kill sessionsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."/.env.*",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from oracle.data_studio_mcp_server.http_runtime import decide_bindFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.from oracle.data_studio_mcp_server.http_runtime import (Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.action_label='kill all sessions')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- [HTTP runtime](oracle/data_studio_mcp_server/http_runtime.py): bind gate and bearer middlewareFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.action_label='kill session')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.'''Passwords in URL userinfo (https://user:pass@host).'''Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# URL with userinfo: https://user:password@hostFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."/.env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.msg = ('Connection to https://weblogic:welcome1@'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from oracle.data_studio_mcp_server.http_runtime import decide_bindFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.essbase_manage_sessions — read/modify: list/kill sessionsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."""Manage Essbase sessions: list active sessions, get current session, kill a session, or kill all sessions.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.from oracle.data_studio_mcp_server.http_runtime import decide_bindFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.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 oracle.data-studio-mcp-server@2.0.0 as of 12 h ago. This is the package itself, not its dependencies.
What would make this Verified
3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim oracle: 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.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- 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.
- URL with embedded credentials≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.