Perplexity Search

PassAudited by ClawScan on May 1, 2026.

Overview

This skill appears narrowly focused on Perplexity search through AIsa, but it will send your prompts to an external API using your AIsa API key.

This looks safe for its stated purpose. Install it only if you intend to use AIsa/Perplexity search, keep the AISA_API_KEY protected, and avoid putting confidential information into search prompts unless that matches your data-sharing expectations.

Findings (2)

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

The skill can make AIsa API calls under your account credential, which may affect account usage or quota.

Why it was flagged

The client reads an AIsa API key from the environment and uses it as a bearer token for the intended 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 or least-privileged AIsa key if available, keep it out of logs, and monitor API usage.

Note

ASI07: Insecure Inter-Agent Communication

What this means

Anything included in the search query may be shared with the external AIsa/Perplexity service.

Why it was flagged

The user query and any optional system instruction are packaged as messages and sent to the external AIsa API.

Skill content

BASE_URL = "https://api.aisa.one/apis/v1" ... body = {"model": model, "messages": messages}

Recommendation

Avoid sending secrets, private documents, or sensitive personal data in queries unless you are comfortable with the provider handling that content.