nmt-diagnose
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted user input, such as product descriptions, metric data, and current business initiatives, to perform strategy diagnostics.
- Ingestion points: User input provided during the conversational diagnostic flow (SKILL.md).
- Boundary markers: The skill lacks formal technical delimiters for untrusted input, though it instructs the agent to treat user-reported data as claims or hypotheses rather than verified facts.
- Capability inventory: The skill has the capability to write diagnostic results to a local file (markdown or HTML) within the
Skills-Results/directory upon user request (SKILL.md). - Sanitization: There are no explicit sanitization, filtering, or escaping mechanisms described for the data provided by the user before it is interpolated into the analysis process.
- [NO_CODE]: The skill consists exclusively of markdown instructions and documentation without including any executable scripts, binaries, or configuration files that run code.
Audit Metadata