optimizing-onboarding
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown designed to guide the agent in user onboarding optimization. It does not contain executable code, scripts, or network operations.
- [NO_CODE]: The skill is purely instructional and does not include any accompanying scripts, executables, or code files.
- [INDIRECT_PROMPT_INJECTION]: The skill references external data sources to gain context, which is a potential surface for indirect injection.
- Ingestion points: The skill reads the files .claude/product-marketing-context.md and references/experiments.md to customize its behavior.
- Boundary markers: No delimiters or instructions to ignore embedded content are present.
- Capability inventory: The skill has no executable tools, scripts, or network capabilities.
- Sanitization: No validation or sanitization is performed on the ingested content. The absence of executable capabilities prevents this surface from being exploited for malicious actions beyond influencing the agent's textual output.
Audit Metadata