Multi Search
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a coherent instruction-only deep-research workflow, but users should be aware it can launch multiple research subagents, use web retrieval, and write research files from provided material.
This skill appears safe for normal research use. Use it with clear, non-sensitive inputs, confirm how many topics or subagents it will run if needed, and review the generated files before treating them as authoritative or sharing them.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
Running the skill may start several parallel web-research tasks and consume time, tool calls, or quota.
The skill explicitly directs the agent to use multiple subagents and web retrieval tools. This is central to the research purpose and disclosed, but it may create a larger automated tool run than a user expects.
Launch an independent `general-purpose` research agent for each research topic. ... Deep Retrieval Requirements: - 4-6 rounds of deep retrieval - Auto-select WebSearch (discovery) or WebFetch (get full content)
Before invoking it, provide a clear topic list and ask the agent to confirm the number of subagents and retrieval scope if cost, time, or breadth matters.
Sensitive business, legal, or personal context included in the input may be shared across the research subagents and could influence web-search queries.
The skill sends project context to independent research agents. This is expected for parallel research, but the artifacts do not provide detailed boundaries for sensitive or confidential input.
Context Transfer (Main Agent -> Research Agent): - Project key information ... - Complete topic list and retrieval scope for each topic ... - Specific requirement background
Avoid providing confidential material unless you are comfortable with it being used for subagent research context; redact sensitive details when possible.
Generated reports may remain in the workspace and could later be reused or trusted as a knowledge base.
The skill creates persistent research documents from retrieved and generated content. This is appropriate for the stated purpose, but saved research outputs can preserve inaccurate, sensitive, or source-influenced content.
Create directory: `[output-dir]/03 - Deep Research/` ... Generate research overview document (000.Research-Overview.md) ... Integrate core findings from all research agents
Review generated research documents before relying on them, sharing them, or using them as future context.