firecrawl-lead-research

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its core function of scraping and summarizing untrusted web content.
  • Ingestion points: External websites, news articles, and public profiles retrieved via the Firecrawl API as specified in SKILL.md.
  • Boundary markers: Absent; there are no specific instructions or delimiters guiding the agent to ignore or isolate instructions found within the scraped text.
  • Capability inventory: The skill aggregates and synthesizes external data into a structured intelligence brief.
  • Sanitization: The skill does not implement sanitization or validation of the content fetched from external sources.
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from external web sources (company websites, news, and profiles) using the Firecrawl service to perform research.
  • [NO_CODE]: The skill consists entirely of instructional prompts and does not contain any scripts, binaries, or executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:48 PM