firecrawl-agent
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx firecrawl, which downloads thefirecrawlpackage from the NPM registry. This package is the official CLI tool provided by the author for performing data extraction tasks. - [COMMAND_EXECUTION]: The skill provides examples of executing shell commands via the
firecrawlCLI to automate website navigation, data extraction, and writing output to local JSON files using the-oflag. - [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection because it is designed to ingest and process untrusted content from the public internet.
- Ingestion points: The agent fetches data from external websites specified in the
--urlsparameter or navigated to during autonomous extraction (SKILL.md). - Boundary markers: While the skill uses JSON schemas to help the agent structure its output, there are no specific instructions or delimiters provided to prevent the agent from following malicious commands that might be hidden within the fetched web content.
- Capability inventory: The agent uses the
Bashtool to run thefirecrawlCLI, which allows for network access to arbitrary sites and the ability to write files to the local directory. - Sanitization: The skill relies on the
firecrawltool's extraction logic and does not implement additional filtering or sanitization of the remote content before it is processed by the AI.
Audit Metadata