Skills
Navigate
skills/brainfish-ai/webcrawl-anything/webcrawl-research-corpus/Gen Agent Trust Hub

webcrawl-research-corpus

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx webcrawl, which downloads and executes the webcrawl utility from the npm registry at runtime.
  • [COMMAND_EXECUTION]: Instructions involve running shell commands like npx webcrawl map and npx webcrawl crawl to discover URLs and scrape web content into local Markdown files.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites during the crawling process. It mitigates risk by converting content to clean Markdown, adding boundary markers via frontmatter (url, sha256), and focusing on structural headings for RAG chunking.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 10:29 AM