Tech And Internet Domain Search Agent
PassAudited by ClawScan on May 1, 2026.
Overview
This is a coherent instruction-only web research skill, but it relies on external web results and a persistent research log that users should review.
This appears safe to use for ordinary web research. Before installing, be aware that it may create a persistent research log and scrape multiple web pages; avoid sensitive queries unless you know where logs are stored, and ask it to verify important claims across reliable sources.
Findings (4)
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.
Research topics and scraped content may remain in a log and influence later report synthesis.
The skill intentionally stores collected research in a persistent log and keeps the log path in memory; this is useful for research but can preserve sensitive queries or untrusted web content.
Use the `create_wiki_document_simple` tool to create a **Research Log** wiki document... You **must** remember this path in your internal memory. **All data records hereafter will be appended to this log file.**
Avoid using the skill for sensitive topics unless you understand where the wiki document is stored, and review or clear research logs when appropriate.
Low-quality, misleading, or adversarial web pages could be treated as authoritative in the final report.
The skill tells the agent to prioritize external search results very strongly, which is purpose-aligned for current research but can over-trust inaccurate or manipulated web content.
**Real-time information returned by external tools is the only source of truth**... you must unconditionally trust the search results.
Ask the agent to cross-check important claims across authoritative sources and not treat arbitrary web results as inherently reliable.
The agent may fetch several web pages and write research notes as part of normal operation.
The skill uses multiple external search/scraping and document-writing tools. This is expected for a research agent, but the metadata does not explicitly declare these tool dependencies.
**In Parallel**, execute the 3-5 search-type tool calls... Parallel call the `url_scraping` tool... use the `append_to_wiki_document_simple` tool
Use it where web access and research-log writes are acceptable, and review tool permissions if your environment exposes broader tools.
You have less information about who authored or maintains the instructions.
The skill has limited provenance information, although there is no executable install mechanism or code artifact in the provided package.
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Review the instructions before use and prefer skills with clear provenance for sensitive workflows.