customer-health-score
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied business data, such as account metrics and indicator lists, which are then interpolated into a structured health score specification. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the provided data values or labels.
- Ingestion points:
SKILL.md(Interview section and Workflow step 3). - Boundary markers: None explicitly defined to separate user-provided data from agent instructions in the generated output.
- Capability inventory: None; the skill provides instructions for generating specifications and artifacts rather than executing shell commands, file system operations, or network calls.
- Sanitization: No explicit sanitization or validation of the user-provided indicator names or business descriptions is mentioned in the instructions.
Audit Metadata