resolve-before-create
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external CRM data such as names, emails, and company domains, which constitutes an ingestion surface.
- Ingestion points: Incoming contact and account data strings processed by the agent (SKILL.md).
- Boundary markers: No explicit delimiters or boundary markers for external data are suggested.
- Capability inventory: No scripts, tool definitions, or shell commands are included in the skill files.
- Sanitization: The instructions recommend normalization (lowercase, whitespace standardization) for matching purposes, but no security-focused sanitization is present.
- [NO_CODE]: The skill is composed entirely of Markdown documentation and logic instructions. No Python, JavaScript, Shell scripts, or executable files are provided.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access commands were identified.
Audit Metadata