firecrawl-map

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch the firecrawl package from the public npm registry. This is a standard practice for using this well-known scraping utility.
  • [REMOTE_CODE_EXECUTION]: Executes the firecrawl CLI tool directly using npx. Since firecrawl is a well-known technology service, this remote execution is considered a routine function of the skill's purpose.
  • [COMMAND_EXECUTION]: Utilizes bash commands to perform site mapping operations and manage local output files within the .firecrawl directory.
  • [PROMPT_INJECTION]: The skill ingests untrusted data in the form of website structures and URLs, presenting a surface for indirect prompt injection. This is an inherent risk common to all web-discovery and scraping tools. Evidence: 1. Ingestion points: External website structures and URL lists (SKILL.md). 2. Boundary markers: Absent from the recommended prompt interpolation. 3. Capability inventory: Bash command execution and local file writing (SKILL.md). 4. Sanitization: Not explicitly specified in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 06:16 AM