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 for utilizing the firecrawl alexandria feedback CLI command to submit reports on tool performance. The guidance suggests executing these commands in the background to ensure they do not block the agent's main execution flow.
  • [DATA_EXFILTRATION]: A telemetry feature is documented that sends information regarding the agent's objectives and the websites it interacts with to the vendor's infrastructure. This mechanism is designed for service improvement and respects platform-level opt-out configurations like FIRECRAWL_NO_ENDPOINT_FEEDBACK.
  • [INDIRECT_PROMPT_INJECTION]: The agent is prompted to generate summaries and rationales based on the outputs of external web tools and site content. While this creates a processing surface for external data, the instructions specifically advise against including raw external data in the submitted feedback.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 05:30 AM