seo-audit

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of retrieving and analyzing data from external web pages.
  • Ingestion points: Untrusted HTML data from external websites is ingested via the referenced scripts/fetch_page.py script in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat crawled content as data rather than instructions.
  • Capability inventory: The skill has the capability to execute local scripts (scripts/fetch_page.py), write multiple files (FULL-AUDIT-REPORT.md, ACTION-PLAN.md), and delegate tasks to several sub-agents.
  • Sanitization: The skill description contains no mention of sanitizing or validating the crawled HTML content before it is processed by the orchestrator or sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 02:09 PM
Security Audit — agent-trust-hub — seo-audit