seo-expert-kit

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to analyze external websites, which introduces a surface for indirect prompt injection. Malicious instructions on a target site could potentially influence the agent's behavior during an audit.
  • Ingestion points: Target URLs processed by scripts/content_audit.js and scripts/content_audit.py.
  • Boundary markers: Absent in scripts and core instructions.
  • Capability inventory: Execution of local diagnostic scripts.
  • Sanitization: No content filtering is performed by the provided scripts.
  • [COMMAND_EXECUTION]: The skill includes Node.js and Python scripts for SEO auditing. These are safe, local scripts that currently only log status messages and do not interact with the network or sensitive files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:04 PM