Openclaw Aisa Web Search Tavily Hardened

PassAudited by VirusTotal on May 10, 2026.

Overview

Type: OpenClaw Skill Name: openclaw-aisa-web-search-tavily-hardened Version: 1.0.0 The skill bundle provides legitimate web search and content extraction capabilities via the AIsa API gateway. The Node.js scripts (search.mjs and extract.mjs) are transparent, well-documented, and contain no malicious logic, obfuscation, or unauthorized data exfiltration. Furthermore, SKILL.md and SAFETY.md include proactive safety guardrails designed to prevent the AI agent from engaging in unauthorized scraping or data exfiltration.

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.

Note

ASI03: Identity and Privilege Abuse

What this means

Your AIsa API key is needed to run searches and may consume your provider quota.

Why it was flagged

The skill reads AISA_API_KEY from the environment and uses it as a bearer token for the AIsa API. This is expected for the stated service integration, and the artifacts do not show logging, hardcoding, or unrelated use of the credential.

Skill content

const apiKey = (process.env.AISA_API_KEY ?? "").trim(); ... "Authorization": `Bearer ${apiKey}`,

Recommendation

Use a dedicated or limited-scope AIsa key if available, keep it out of shared logs, and unset it when not needed.

Note

ASI07: Insecure Inter-Agent Communication

What this means

AIsa/Tavily can receive the searches you run, and the extract script similarly sends requested URLs to the provider.

Why it was flagged

Search requests are sent to AIsa's external API gateway. This is disclosed and purpose-aligned, but it means user-provided search terms leave the local environment.

Skill content

await fetch("https://api.aisa.one/apis/v1/tavily/search", { ... body: JSON.stringify(body), });

Recommendation

Avoid sending confidential queries, private URLs, or sensitive internal information unless you are comfortable with AIsa's handling of that data.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

You have less independent provenance information about who maintains the skill or where the published code came from.

Why it was flagged

The registry metadata does not provide a source repository. The included code is present and there is no install spec or remote installer, so this is a provenance note rather than evidence of unsafe behavior.

Skill content

Source: unknown

Recommendation

Prefer installing from a trusted registry account, and review the included scripts before use if provenance matters for your environment.