Lite Research
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
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.
NoteHigh Confidence
ASI02: Tool Misuse and ExploitationWhat this means
The agent may send your research topic and generated search queries to web/search tools, then use fetched web pages to produce a summary.
Why it was flagged
The skill relies on external web-search and web-fetch tools. This is purpose-aligned and bounded by the documented maximum of 5 queries and 5 results per query, but it is still a tool-use behavior users should notice.
Skill content
Uses web_search to find results for multiple related queries... Uses web_fetch to read the top 5 results for each query
Recommendation
Use it for public or non-sensitive research topics, review the cited sources, and avoid including private secrets in research prompts.