seo-plan

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data from external URLs.
  • Ingestion points: External Website and Competitor URLs are ingested through the 'Input Required' parameters in SKILL.md.
  • Boundary markers: None identified; there are no instructions to the agent to treat scraped data as untrusted or ignore instructions within it.
  • Capability inventory: The skill uses internal scripts (competitor-scraper.py, tech-seo-auditor.py) to process this external data.
  • Sanitization: No sanitization or filtering logic is specified for the external content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 12:41 AM
Security Audit — agent-trust-hub — seo-plan