seo-content-auditor

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (LOW): Indirect Prompt Injection Surface.
  • Ingestion points: The skill is designed to ingest and analyze untrusted external content (SEO audit targets) during runtime.
  • Boundary markers: Absent. The instructions do not define delimiters (e.g., XML tags or triple quotes) to separate the system instructions from the analyzed content.
  • Capability inventory: The skill has no capability for command execution, network access, or file modification. It only reads a local documentation file (implementation-playbook.md) and produces text output.
  • Sanitization: Absent. No validation or filtering is performed on the ingested content.
  • Risk Analysis: An attacker could embed instructions in a website's text to manipulate the agent's audit score or recommendations, but the impact is contained within the local session context.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 12:56 AM