firecrawl-interact

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from arbitrary external URLs via the scrape and interact commands, creating a potential attack surface. [Ingestion points]: Web content fetched from external URLs via firecrawl scrape. [Boundary markers]: Absent; the skill does not include specific delimiters or warnings for the agent to ignore instructions within the scraped data. [Capability inventory]: Access to Bash command execution for the Firecrawl CLI and browser automation via agent-browser scripts. [Sanitization]: No sanitization of ingested content is mentioned.
  • [DYNAMIC_EXECUTION]: The skill utilizes the --code flag to execute browser automation instructions (e.g., agent-browser click) at runtime.
  • [EXTERNAL_DOWNLOADS]: The skill instructions involve npx firecrawl-cli, which downloads the Firecrawl CLI package from the npm registry. As this is a vendor-owned resource, this is documented as expected behavior.
  • [COMMAND_EXECUTION]: The skill is configured to run shell commands via Bash(firecrawl *) and Bash(npx firecrawl-cli *) to perform its primary functions of web scraping and interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 03:10 AM
Security Audit — agent-trust-hub — firecrawl-interact