security-architect
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as an instructional guide for security best practices. It correctly demonstrates secure coding techniques, such as using parameterized queries to prevent SQL injection and employing strong hashing for password storage. It also appropriately references services like Cloudflare, AWS, and Stripe as examples of security controls and providers.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze project source code and documentation, which constitutes a potential attack surface for indirect prompt injection if an attacker embeds instructions within those files.
- Ingestion points: Analyzes local project files during threat modeling and code reviews.
- Boundary markers: None specified in the instructions to differentiate between code to be analyzed and instructions for the agent.
- Capability inventory: The skill has file system write access ('modifies_files') and can create artifacts.
- Sanitization: No explicit instructions are provided to sanitize or ignore instructions embedded within the code being reviewed.
Audit Metadata