10-reverse-kpi-global
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions and benchmark data. It does not include any scripts, executables, or commands.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read product marketing context from a local file (
.agents/product-marketing-context-global.md). While reading external data can be an attack surface, the skill does not possess any dangerous capabilities (like network access or shell execution) that could be triggered by malicious content in that file.
Audit Metadata