webcrawl-learn-topic
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill invokes
npx webcrawl, which performs a download and execution of the webcrawl utility from the npm registry. This tool originates from the author's identified repository and is used for its intended purpose of retrieving web content. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the internet, creating a potential surface for indirect prompt injection.
- Ingestion points: Content is ingested from various third-party websites during search and crawl operations described in SKILL.md.
- Boundary markers: The skill does not provide instructions to use protective delimiters or specific ignored sections when processing newly scraped web data.
- Capability inventory: The agent's capabilities include searching, scraping, and mapping website structures using the webcrawl CLI.
- Sanitization: Although the tool converts HTML into clean Markdown, there is no verification layer to detect or filter adversarial linguistic commands embedded within that data.
Audit Metadata