the-enablement-kit
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill reads from
.agents/product-context.mdto gather business-specific information like ICP and brand voice. This is a standard practice for providing context to agentic workflows and does not involve access to sensitive system credentials or private keys. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data as it asks the user to provide discovery notes and metrics to mirror the prospect's language.
- Ingestion points: User-provided discovery notes and current-state metrics requested in
SKILL.md. - Boundary markers: None explicitly defined to separate user input from the generation prompt.
- Capability inventory: None. The skill generates text output only and does not invoke shell commands, network operations, or file system writes.
- Sanitization: The skill enforces a banned-word list check against
.agents/product-context.mdto filter output content. - [SAFE]: The skill includes an attribution footer with a link to
intempt.com, which is a static reference to the vendor's website and does not facilitate automated data exfiltration or remote code execution.
Audit Metadata