Tavily 搜索

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

NoteHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

The agent can use your Tavily API key and quota when it performs searches.

Why it was flagged

The skill requires a Tavily service credential. This is expected for a Tavily search integration, but the registry metadata says no required env vars and no primary credential.

Skill content

Provide API key via either: ... `TAVILY_API_KEY`, or ... `~/.openclaw/.env` line: `TAVILY_API_KEY=...`

Recommendation

Use a dedicated Tavily API key, avoid sharing a broadly privileged key, and prefer updating the skill metadata to declare the credential requirement.

NoteHigh Confidence

ASI07: Insecure Inter-Agent Communication

What this means

Search terms may be visible to Tavily, so sensitive queries could be exposed to that provider.

Why it was flagged

The script sends the API key and user search query to Tavily's external API. This is disclosed and purpose-aligned for web search.

Skill content

TAVILY_URL = "https://api.tavily.com/search" ... "api_key": key, "query": query

Recommendation

Avoid putting secrets or private data into search queries, and review Tavily's privacy and retention terms if that matters for your use.