skills/jeremylongshore/tons-of-skills-marketplace/firecrawl-reference-architecture/Gen Agent Trust Hub
firecrawl-reference-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for automated web ingestion which creates a vulnerability surface where malicious content from scraped websites could influence downstream AI tasks.
- Ingestion points: Data is fetched from external URLs via
firecrawl.scrapeUrl,firecrawl.crawlUrl, andfirecrawl.mapUrlas shown inSKILL.md. - Boundary markers: The provided code templates do not include explicit prompt delimiters or instructions to the agent to ignore embedded commands in the scraped content.
- Capability inventory: The skill includes templates that use
fs.writeFileSyncto save content to the local file system (e.g., insrc/pipeline/crawl-pipeline.ts). - Sanitization: A
cleanMarkdownfunction is provided insrc/pipeline/processor.tswhich performs basic sanitization by removing HTML comments andjavascript:links, though it does not fully neutralize prompt injection patterns.
Audit Metadata