lead-magnets
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest business-specific context and user-provided marketing data (e.g., product descriptions, conversion rates, and existing content) to generate strategy recommendations. This creates a surface for potential indirect prompt injection if an attacker-controlled document is processed. However, the risk is minimal as the skill lacks high-risk capabilities like arbitrary command execution, file writing, or network exfiltration.
- Ingestion points: Reads business context and marketing information from user prompts or project files like
.agents/product-marketing.md. - Boundary markers: None explicitly defined in the prompt templates.
- Capability inventory: The skill provides strategy planning and outlines; it does not perform shell operations, network requests, or file modifications beyond reading context.
- Sanitization: None specified for input data.
Audit Metadata