agent-deep-researchAsync deep research via Gemini Interactions API (no Gemini CLI dependency). RAG-ground queries on local files (--context), preview costs (--dry-run), structu...
Install via ClawdBot CLI:
clawdbot install 24601/agent-deep-researchGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdSends data to undocumented external endpoint (potential exfiltration)
report → https://github.com/24601/agent-deep-research/security/advisories/newPotentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
https://github.com/24601/agent-deep-researchGenerated Mar 20, 2026
Researchers can upload academic papers and use the skill to perform deep research on specific questions, generating structured summaries and identifying gaps in literature. This accelerates literature reviews and supports hypothesis generation.
Business analysts upload competitor reports and market data to conduct RAG-grounded research on industry trends and competitive strategies. The skill outputs detailed reports for strategic decision-making.
Law firms use the skill to analyze legal documents, contracts, and case files by uploading them as context. It helps in extracting key clauses, precedents, and generating legal briefs efficiently.
Developers upload source code directories to research security vulnerabilities, architectural patterns, or documentation gaps. The skill provides insights and recommendations for code improvements.
Medical professionals upload clinical studies and patient data (anonymized) to research treatment efficacy or disease patterns. The skill synthesizes information into actionable reports for healthcare planning.
Offer the skill as a cloud-based service with tiered subscriptions for different usage levels, such as number of research queries or file upload limits. This provides recurring revenue from businesses and researchers.
Integrate the skill into consulting firms' workflows to enhance research capabilities for clients. Charge per project or on a retainer basis for customized research reports and analysis.
License the skill to large enterprises for internal use, such as in R&D departments or legal teams. Include support, customization, and compliance features for a high-value license fee.
💬 Integration Tip
Ensure environment variables like GOOGLE_API_KEY are securely set, and use the --dry-run flag to preview costs and file uploads before executing research tasks.
Scored Apr 16, 2026
Uses known external API (expected, informational)
cloud.google.comAI Analysis
The skill's primary external interaction is with the documented Google Gemini API, which is consistent with its stated purpose. The flagged signals appear to be misinterpretations of documentation (e.g., mentioning /etc/passwd as an example of a sensitive file to avoid, not to access) and references to its own GitHub repository for security reporting, not data exfiltration. The file upload exclusions and credential handling are explicitly documented and appear reasonable.
Audited Apr 16, 2026 · audit v1.0
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.
Perform complex, long-running research tasks using Gemini Deep Research Agent. Use when asked to research topics requiring multi-source synthesis, competitive analysis, market research, or comprehensive technical investigations that benefit from systematic web search and analysis.
Deep multi-source research via Parallel API. Use when user explicitly asks for thorough research, comprehensive analysis, or investigation of a topic. For quick lookups or news, use parallel-search instead.
AI deep research powered by CellCog. Market research, competitive analysis, investment research, academic research, due diligence, literature reviews with ci...
Get Shit Done - Full project planning and execution workflow. Handles project initialization with deep context gathering, automated research, roadmap creation, phase planning, and execution with verification.