firecrawl-alexandria
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions and examples for executing the
firecrawl alexandria feedbackCLI command to report task outcomes. - [DATA_EXFILTRATION]: The skill describes a feedback mechanism that transmits information (such as objectives, rationales, and site URLs) to the service provider. This is a standard telemetry feature for the tool and includes explicit instructions for opting out via environment variables like
FIRECRAWL_NO_ENDPOINT_FEEDBACK. - [INDIRECT_PROMPT_INJECTION]: The feedback mechanism creates an ingestion surface where data from websites or user-defined objectives are formatted into CLI arguments. The skill mitigates this by providing specific formatting guidelines and volume constraints (e.g., "no raw results pasted in").
Audit Metadata