Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Galileo python sdk
v1.2.1Complete reference for the Galileo AI platform Python SDK for evaluating, observing, and protecting GenAI applications. Use when building Python applications...
⭐ 0· 0·0 current·0 all-time
byGyanesh Malhotra@gyanesh-m
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The name and description match the SKILL.md content: this is a reference for the Galileo Python SDK (evaluation, observability, guardrails). The capabilities described (tracing, metrics, guardrails, integrations) align with the stated purpose.
Instruction Scope
The runtime instructions direct the agent/developer to instrument many frameworks and to auto-log/traces LLM calls, then upload traces via HTTP to https://app.galileo.ai/api/otel/v1/traces and other Galileo endpoints. That behavior is consistent with an observability SDK, but it means prompts, inputs, outputs, and possibly PII will be captured and transmitted. The SKILL.md also demonstrates using OPENAI_API_KEY and GALILEO_API_KEY from the environment even though the skill metadata declared no required env vars—this is an important scope mismatch.
Install Mechanism
This is an instruction-only skill with no install spec or code files in the registry bundle. The doc recommends pip install commands (galileo, promptquality, galileo-protect), which is expected for a Python SDK reference and represents normal, low-risk guidance.
Credentials
The SKILL.md clearly requires secrets/environment variables (GALILEO_API_KEY, GALILEO_CONSOLE_URL, optional GALILEO_PROJECT, GALILEO_LOG_STREAM, and examples referencing OPENAI_API_KEY) but registry metadata lists no required env vars or primary credential. Requesting GALILEO_API_KEY is proportionate to the SDK’s function, but the manifest omission is a mismatch that could mislead users about what credentials will be accessed or required.
Persistence & Privilege
The skill does not request always:true, does not install or persist code via an install spec, and does not claim to modify other skills or system-wide settings. Autonomous invocation is allowed (default) but not combined with other elevated privileges here.
What to consider before installing
This appears to be legitimate Galileo SDK documentation, but there are two issues you should consider before using it: (1) the skill metadata does not declare the environment variables that the instructions actually use—GALILEO_API_KEY (and examples using OPENAI_API_KEY) are required for the SDK to send traces to Galileo; (2) the SDK’s instrumentation will capture and transmit LLM inputs, outputs, and other runtime data to https://app.galileo.ai (or a self-hosted console URL), which may include sensitive or regulated data. Actions to take before installing/using: verify the skill source (confirm the GitHub repo and official documentation), only set GALILEO_API_KEY from a trusted vendor-provided key, avoid enabling automatic instrumentation in environments with sensitive data, prefer a self-hosted console URL if your organization requires it, limit which frameworks/components are instrumented, and test in an isolated environment while monitoring network traffic. Also ask the publisher to correct the skill manifest to list required env vars and a homepage so the credential usage is explicit.Like a lobster shell, security has layers — review code before you run it.
latestvk975wbjymvqvc46qd5gq0en2en84rayz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.