Intelligent Search Agent

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.

What this means

It may be harder for a user to independently verify the code origin or update history before installing.

Why it was flagged

The skill includes a Python client but the registry metadata does not identify a source repository or provenance beyond the listed homepage.

Skill content
Source: unknown
Recommendation

Install only if you trust the publisher or registry entry, and review the included script before use.

What this means

Anyone or any agent using this skill with that environment variable can make requests under the user's AIsa API credential.

Why it was flagged

The client reads AISA_API_KEY from the environment and uses it as a bearer token for all API requests.

Skill content
self.api_key = api_key or os.environ.get("AISA_API_KEY") ... "Authorization": f"Bearer {self.api_key}"
Recommendation

Use a dedicated, least-privilege API key where possible, keep it out of prompts and logs, and rotate it if exposure is suspected.

What this means

Search prompts, research questions, and URLs may leave the local agent environment and be processed by external services.

Why it was flagged

User-supplied queries, and optionally system-style instructions, are sent to an external AIsa API gateway for Perplexity-style answer generation.

Skill content
BASE_URL = "https://api.aisa.one/apis/v1" ... messages.append({"role": "user", "content": query}) ... data={"model": model, "messages": messages}
Recommendation

Avoid sending secrets, private documents, or confidential internal URLs as search queries unless that is acceptable under the provider's data-handling terms.