churn-prevention
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a processing surface for external context which could be leveraged for indirect prompt injection.
- Ingestion points: Instructions in SKILL.md direct the agent to read marketing and product context from local files such as .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md before proceeding.
- Boundary markers: The skill lacks explicit boundary markers or delimiters to separate the ingested context from the system instructions, nor does it include warnings to ignore instructions embedded within those files.
- Capability inventory: The skill identifies several CLI tools for operational use, including stripe, customer-io, posthog, mixpanel, ga4, and segment (documented in SKILL.md).
- Sanitization: There are no instructions for sanitizing or validating the content of the external context files before they are incorporated into the agent's reasoning process.
Audit Metadata