dotnet-architect
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOW
Full Analysis
- PROMPT_INJECTION (SAFE): No evidence of instructions attempting to bypass safety filters, override system prompts, or extract internal instructions was found. The persona is strictly focused on .NET architectural guidance.
- DATA_EXFILTRATION (SAFE): There are no network calls (curl, wget, etc.) or access requests to sensitive system files like credentials or SSH keys. All instructions are localized to the agent's task.
- REMOTE_CODE_EXECUTION (SAFE): The skill does not download or execute remote scripts. It provides code examples in a static, descriptive manner without calling interpreters or runtime compilers.
- OBFUSCATION (SAFE): The content is clear and readable. No Base64 encoding, zero-width characters, or hidden Unicode tags were detected in the instructions or examples.
- INDIRECT_PROMPT_INJECTION (LOW): While the skill references an external file (
resources/implementation-playbook.md), this is a standard local dependency for context retrieval. There are no side-effect capabilities (like file writes or command execution) that would make it vulnerable to high-risk injection attacks.
Audit Metadata