firecrawl-search
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
firecrawlandnpx firecrawlto perform searches and content extraction. - [EXTERNAL_DOWNLOADS]: Uses
npxto dynamically fetch thefirecrawlpackage from the npm registry. - [PROMPT_INJECTION]: Subject to indirect prompt injection risks due to the ingestion of untrusted external web content.
- Ingestion points: Scraped web content and search metadata from external sites are saved to the
.firecrawl/directory and subsequently processed by the agent. - Boundary markers: No explicit delimiters or instructions are provided to help the agent distinguish between tool output and potential malicious instructions within the scraped content.
- Capability inventory: The skill possesses file system write access and the ability to execute shell commands via the
Bashtool. - Sanitization: The skill does not implement sanitization or filtering of the markdown or JSON content retrieved from external URLs.
Audit Metadata