firecrawl-scraper
Warn
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation instructions direct users to fetch a package from a community GitHub repository (
BenedictKing/firecrawl-scraper) usingnpx skills add. This involves the execution and integration of code from an external source that is not part of a recognized trusted organization. - [PROMPT_INJECTION]: As the skill is designed to ingest and process content from arbitrary web pages, it is vulnerable to indirect prompt injection. Malicious instructions hidden within scraped websites could potentially influence the agent's logic or behavior.
- Ingestion points: External web content, including HTML, text, and PDF data retrieved via the Firecrawl API.
- Boundary markers: The skill documentation does not specify the use of delimiters or instructions to ignore embedded commands within the scraped data.
- Capability inventory: Deep scraping, browser interaction (clicking, scrolling), and automated batch processing of URLs.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is presented to the agent's context.
Audit Metadata