firecrawl-interact
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to runfirecrawlandnpx firecrawlcommands. It also includes an--interact --codeflag that executes scripts in Bash, Python, or Node.js to control browser sessions. - [EXTERNAL_DOWNLOADS]: The skill uses
npx firecrawl, which downloads thefirecrawlpackage from the NPM registry, a well-known and trusted service. - [REMOTE_CODE_EXECUTION]: The
--codeparameter allows for the execution of dynamic scripts within a browser environment as a primary feature of the interaction tool. - [DATA_EXFILTRATION]: The skill can access and persist sensitive browser state (cookies, storage) through the
--profileflag and can save extracted data to local files using the--outputoption. - [PROMPT_INJECTION]: Indirect prompt injection surface detected. 1. Ingestion points: Scraped web pages from
firecrawl scrape. 2. Boundary markers: Absent in the instructions. 3. Capability inventory: Execution of shell commands and scripts viafirecrawl interact --code. 4. Sanitization: No evidence of content sanitization before influencing browser actions.
Audit Metadata