firecrawl-scrape
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for executing the Firecrawl CLI using
Bash(firecrawl *)andBash(npx firecrawl *). These commands are used to scrape web content and save it to the local file system. - [EXTERNAL_DOWNLOADS]: The skill utilizes
npx firecrawlto execute the Firecrawl CLI, which involves fetching the package from the public npm registry at runtime. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest content from arbitrary external URLs, creating a surface for indirect prompt injection attacks.
- Ingestion points: Webpage content fetched through the
firecrawl scrapecommand. - Boundary markers: The instructions do not include specific delimiters or warnings to the agent to treat the scraped content as data rather than instructions.
- Capability inventory: The agent has access to shell execution via Bash and the ability to write files to the disk using the
-ooutput flag. - Sanitization: Although the tool mentions returning clean, LLM-optimized markdown and provides a
--redact-piiflag, it does not provide mechanisms to sanitize the content for embedded malicious instructions that could target the agent's logic.
Audit Metadata