firecrawl-interact

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the firecrawl CLI and npx firecrawl via the Bash tool to perform browser automation. It supports a --code flag for executing bash, python, or node logic specifically within the context of the browser session. This functionality is scoped to the firecrawl toolset within the skill's environment configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and interact with content from arbitrary external URLs.
  • Ingestion points: Content is retrieved from live browser sessions and scraped web pages via the firecrawl scrape and firecrawl interact commands.
  • Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore command-like patterns found within the scraped web content.
  • Capability inventory: The agent has access to Bash(firecrawl *), Bash(npx firecrawl *), and the firecrawl_interact MCP tool to perform browser operations and file writes via the -o flag.
  • Sanitization: No specific sanitization or filtering of the scraped content is implemented before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 02:11 AM