firecrawl-interact

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with live web pages and execute actions based on content found there. This creates a surface for instructions embedded in malicious web pages to influence the agent's behavior.
  • Ingestion points: External web content retrieved via firecrawl scrape and subsequent firecrawl interact sessions in SKILL.md.
  • Boundary markers: None documented in the instructions; the agent interprets page content directly to perform actions.
  • Capability inventory: Extensive browser control including clicking, form filling, and data extraction using the firecrawl toolset.
  • Sanitization: No explicit sanitization or filtering of web content before interaction is mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill documentation suggests using npx firecrawl-cli, which involves downloading and executing the CLI package from the public NPM registry. This is a standard distribution method for the vendor's tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:28 PM
Security Audit — agent-trust-hub — firecrawl-interact