firecrawl-research-index

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is focused on legitimate academic and technical research tasks. Its behavior is entirely consistent with the stated purpose of finding and analyzing scientific literature.
  • [EXTERNAL_DOWNLOADS]: The skill uses firecrawl_scrape and firecrawl_search to fetch data from the internet. This is a functional requirement for retrieving paper metadata and web-based research benchmarks.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from research papers and the web. Ingestion points: firecrawl_scrape and firecrawl_read_paper in SKILL.md. Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore commands within the source text. Capability inventory: The skill is restricted to research-specific search and read tools; it lacks capabilities for arbitrary shell execution, filesystem access, or credential exfiltration. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 05:03 PM
Security Audit — agent-trust-hub — firecrawl-research-index