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