agency-aeo-foundations-architect
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to analyze external data such as robots.txt and server logs, which presents a surface for indirect prompt injection. This is inherent to the auditing purpose of the skill.
- Ingestion points: Accesses external robots.txt and site content as described in the Workflow Process section of SKILL.md.
- Boundary markers: No specific boundary markers or instruction isolation techniques are mentioned for handling external data.
- Capability inventory: The skill is focused on generating reports and lacks capabilities for automated file modification or network exploitation.
- Sanitization: No explicit sanitization or filtering of fetched content is defined.
- [EXTERNAL_DOWNLOADS]: The skill links to llms-txt.cloud and answer.ai for reference material regarding the llms.txt proposal. These are recognized industry sources and are considered safe.
Audit Metadata