Deep Research Pro

OpenClaw analysis

The skill's runtime instructions ask the agent to run absolute-path helper scripts, fetch many web pages with curl, save files, and spawn sub-agents, but the registry metadata does not declare those external script dependencies or config paths — this mismatch and the broad web-fetch behavior merit caution.

Confidence: medium

VirusTotal

Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill The skill is designed for multi-source deep research, which inherently involves fetching web content. The `SKILL.md` instructs the agent to use `curl -sL "<url>"` to retrieve web pages and a Python one-liner to process them, which is a necessary and standard operation for its stated purpose. File writing is confined to `~/clawd/research/` for saving reports. The prompt instructions for sub-agent usage are self-referential, aiming to keep the agent on task rather than subverting its behavior. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection designed to compromise the agent or system.