seo-audit

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill framework requires the agent to ingest and analyze external data to find 'evidence' for SEO issues.
  • Ingestion points: External URLs, HTTP headers, and reports from tools like Google Search Console or PageSpeed Insights (sub-skills/findings-classification-required-scoring-aligned.md).
  • Boundary markers: The instructions do not include requirements for using delimiters or warnings to ignore instructions embedded in the analyzed data.
  • Capability inventory: No executable scripts or code files are included with the skill (SKILL.md).
  • Sanitization: No explicit sanitization or validation of external content is defined in the audit guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:04 PM