firecrawl-deep-research

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize large amounts of untrusted data from the open web, creating a surface where malicious instructions embedded in web pages could influence the agent's behavior.
  • Ingestion points: Data is collected from external websites using Firecrawl search and scrape operations as described in SKILL.md under the 'Firecrawl Collection Plan'.
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the scraped content before it is processed for synthesis.
  • Capability inventory: The skill utilizes Firecrawl CLI tools for web navigation and data retrieval, followed by a synthesis step to produce a formal Markdown report.
  • Sanitization: There are no explicit instructions for sanitizing, escaping, or filtering the retrieved web content to prevent the execution of embedded prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:14 PM
Security Audit — agent-trust-hub — firecrawl-deep-research