skills/89jobrien/steve/seo-analysis/Gen Agent Trust Hub

seo-analysis

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze untrusted data from external websites.
  • Ingestion points: Site structure, meta tags, and page content accessed during technical SEO audits (SKILL.md).
  • Boundary markers: Absent; there are no instructions for the agent to ignore or delimit embedded commands within the data it audits.
  • Capability inventory: No executable code is present in the skill, but the agent's underlying browsing and output tools represent the potential impact surface.
  • Sanitization: None; the skill does not specify any sanitization or validation of the external content before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:08 PM