onboarding-cro
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is primarily instructional and does not include any executable scripts, binary files, or automated commands. All identified patterns are limited to professional optimization strategies, frameworks for conversion rate optimization, and experiment lists.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions include a step to read an external context file, which creates a theoretical surface for indirect instructions to be processed.\n
- Ingestion points: The skill reads
.claude/product-marketing-context.mdif it exists in the environment.\n - Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands within the context file.\n
- Capability inventory: None. The skill is designed to generate text-based recommendations, audit reports, and optimization plans. It lacks capabilities for subprocess execution, file-system writes, or network operations.\n
- Sanitization: Absent.
Audit Metadata