plan-aeo-readiness

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for auditing and planning purposes only. It explicitly instructs the agent to 'Audit & plan only' and 'Change nothing until approved,' which prevents unauthorized modifications to the user's environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by auditing external website content (robots.txt, HTML, schema). While this creates an entry point for instructions embedded in third-party websites, the skill's capabilities are limited to generating a markdown report, which significantly mitigates the risk of successful exploitation.
  • Ingestion points: Reads external website files and content during the audit phase.
  • Boundary markers: None explicitly defined for untrusted content.
  • Capability inventory: Limited to writing a plan file (plan-aeo-readiness.md). No subprocess calls or dynamic execution patterns are present.
  • Sanitization: No specific sanitization or escaping of audited content is mentioned before it is included in the plan output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 11:19 AM
Security Audit — agent-trust-hub — plan-aeo-readiness