firecrawl
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation instructs the installation of the official
firecrawl-clipackage from the NPM registry. - Evidence:
npm install -g firecrawl-cli@1.8.0andnpx -y firecrawl-cli@1.8.0 initinrules/install.md. - Note: This is an expected installation from a well-known service.
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to executefirecrawlCLI commands for web interaction. - Evidence:
Bash(firecrawl *)andBash(npx firecrawl *)are defined as allowed tools inSKILL.md. - Evidence: The
firecrawl browser "eval <js>"command enables the execution of JavaScript in a remote browser environment for automation purposes. - [PROMPT_INJECTION]: As a web scraping tool, the skill ingests content from external, untrusted sources, which constitutes a risk for indirect prompt injection.
- Ingestion points: Data is fetched via commands such as
scrape,search,crawl, andagent. - Capability inventory: The skill has the ability to write to the local filesystem and execute shell commands.
- Mitigation: The skill includes
rules/security.md, which defines a security strategy involving file-based isolation in.firecrawl/and incremental reading (e.g., usinggrep,head) to limit the impact of potentially malicious instructions within scraped data.
Audit Metadata