firecrawl-seo-audit

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from external websites to perform SEO audits. This introduces an attack surface for indirect prompt injection.
  • Ingestion points: SKILL.md instructions to 'Map the site' and 'Scrape key pages'.
  • Boundary markers: Absent; there are no specific instructions to ignore embedded commands in the scraped content.
  • Capability inventory: Performs network reads via the Firecrawl API toolset.
  • Sanitization: Absent; the agent is instructed to extract and process text hierarchy and metadata directly. This risk is inherent to the skill's purpose and does not represent a malicious intent.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill requires a 'FIRECRAWL_API_KEY'. This is managed through a standard input parameter, which is a safe practice for handling secrets. No hardcoded credentials or sensitive local file access patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 12:46 PM
Security Audit — agent-trust-hub — firecrawl-seo-audit