saas-router
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes natural language input from users to determine routing logic for the SaaS build lifecycle, which serves as an attack surface for instruction injection.
- Ingestion points: User project descriptions captured via trigger phrases and routing questions (SKILL.md).
- Boundary markers: No boundary markers or specific "ignore embedded instructions" warnings are utilized when processing user input.
- Capability inventory: The skill acts as a gateway to multiple high-privilege operations including authentication setup, payment processing, and deployment (SKILL.md).
- Sanitization: No sanitization or input validation is performed on the user descriptions before they are used for classification.
- [EXTERNAL_DOWNLOADS]: The skill suggests the installation of companion plugins such as
saas-legal-docs,proof-first, andlanding-moment(SKILL.md). These are identified as vendor-owned resources from the authormartinoliveroand represent modular additions to the primary toolset.
Audit Metadata