churn-prevention
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown-formatted instructions and reference guides for business logic and UI design. No evidence of malicious behavior, credential theft, or unauthorized network access was found.
- [NO_CODE]: There are no executable files or scripts (e.g., Python, Node.js, or shell scripts) included in the skill package. All functionality is delivered through instructional text.
- [PROMPT_INJECTION]: The skill instructs the agent to read business context from a local file,
.agents/product-marketing-context.md. While this constitutes an indirect prompt injection surface, it is a standard mechanism for agent personalization and lacks any associated high-risk capabilities (such as code execution or network requests) within the skill's own scope. - Ingestion points:
.agents/product-marketing-context.md(referenced in SKILL.md) - Boundary markers: None provided in the file-reading instructions.
- Capability inventory: No scripts or automated capabilities are present in the skill files.
- Sanitization: No explicit sanitization or filtering logic is defined for the ingested context data.
Audit Metadata