presearch

PassAudited by ClawScan on May 1, 2026.

Overview

This is a simple Presearch API instruction skill; it is purpose-aligned, but users should know it sends queries to an external service and expects a bearer API key.

This skill appears benign and limited to documenting Presearch API usage. Before installing or using it, be aware that your search queries go to Presearch and that you may need to provide a Presearch API key; avoid sending secrets or highly sensitive information in queries.

Findings (3)

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.

Low

#ASI03: Identity and Privilege Abuse

What this means

The agent may need access to a Presearch API key to use this skill.

Why it was flagged

The skill expects a Presearch API key, even though the registry metadata lists no primary credential or required environment variables. This is expected for the API integration, but users should notice the credential requirement.

Skill content

**Auth:** Bearer Token ... Authorization: Bearer YOUR_API_KEY_HERE

Recommendation

Use a dedicated, least-privilege API key if available, and avoid pasting broader credentials into chat or shared logs.

Info

#ASI07: Insecure Inter-Agent Communication

What this means

Search terms may reveal interests, projects, or other sensitive context to the external search provider.

Why it was flagged

The documented workflow sends user search queries to an external Presearch API endpoint. This is core to the skill's purpose and clearly disclosed.

Skill content

**Endpoint:** `https://na-us-1.presearch.com/v1/search` ... `q` | string | ✅ | - | Search query

Recommendation

Avoid sending secrets, private identifiers, or sensitive internal details as search queries unless you are comfortable sharing them with the provider.

Info

#ASI09: Human-Agent Trust Exploitation

What this means

Users might assume stronger privacy guarantees than the artifact itself proves.

Why it was flagged

The artifact makes broad privacy claims. There is no conflicting evidence, but the instruction-only artifact does not substantiate these claims beyond stating them.

Skill content

## Privacy Features
- No tracking or profiling
- Decentralized node network
- Encrypted traffic
- Uncensored results

Recommendation

Treat the privacy claims as provider claims and review Presearch's own documentation or policy before sending sensitive queries.