marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions direct the agent to read external files for product marketing context (e.g.,
.agents/product-marketing.mdor.claude/product-marketing.md). This creates a surface for indirect prompt injection if these files are populated with untrusted content. - Ingestion points:
SKILL.md(instructions to read context files). - Boundary markers: None identified; instructions do not explicitly warn the agent to ignore instructions embedded within the marketing context files.
- Capability inventory: The skill is designed for an agent to generate marketing strategies and provide implementation steps. The surrounding agent likely has message generation and file reading capabilities.
- Sanitization: None identified.
Audit Metadata