referrals
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Detailed analysis of the skill instructions, reference materials, and evaluation prompts revealed no malicious patterns or security vulnerabilities. The skill adheres to its stated purpose of providing growth marketing expertise.
- [PROMPT_INJECTION]: The skill utilizes standard instructional framing to establish its role as a marketing expert. No attempts to bypass safety filters, ignore previous instructions, or extract system prompts were identified.
- [DATA_EXPOSURE]: The skill does not contain hardcoded credentials, API keys, or private keys. It references local marketing context files (e.g.,
.agents/product-marketing.md) to provide tailored advice, which is a standard functional pattern and not a security risk. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by reading external marketing context files, but the potential impact is limited to generating advisory text.
- Ingestion points:
.agents/product-marketing.md,.claude/product-marketing.md,product-marketing-context.md(specified in SKILL.md). - Boundary markers: None identified.
- Capability inventory: Text generation for marketing strategies and email sequences (SKILL.md, references/affiliate-programs.md).
- Sanitization: None identified.
Audit Metadata