education-program
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were identified. The skill content is restricted to strategic and marketing advice.
- [DATA_EXPOSURE]: The skill instructs the agent to read marketing context from
.claude/product-marketing-context.mdor.cursor/product-marketing-context.md. This is a standard operation for context-aware agents to personalize their output based on local project metadata and does not involve sensitive system files or credentials. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits a surface for indirect injection by reading external context files.
- Ingestion points: Reads
.claude/product-marketing-context.mdand.cursor/product-marketing-context.md(SKILL.md). - Boundary markers: Absent.
- Capability inventory: None. The skill only generates marketing recommendations and has no access to subprocesses, network tools, or file-writing capabilities.
- Sanitization: Absent.
Audit Metadata