referral-program
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected across the analyzed files. The skill functions as a knowledge base for marketing strategies.
- [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface by reading from
.claude/product-marketing-context.mdto gather background information. - Ingestion points: Reads
.claude/product-marketing-context.md(SKILL.md). - Boundary markers: Absent; the skill does not wrap the content in delimiters or include instructions to ignore embedded commands.
- Capability inventory: None detected. The skill only generates text-based marketing advice and does not possess capabilities for file writing, network operations, or command execution.
- Sanitization: Absent; external context is interpolated directly into the agent's logic.
Audit Metadata