eda-architect
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The skill does not contain instructions that attempt to override agent safety protocols or bypass system constraints. All instructions are focused on the electronics design workflow.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths (e.g., SSH keys, AWS configs), or unauthorized network communication patterns were identified.
- [Obfuscation] (SAFE): The skill content is clear and readable. No Base64, zero-width characters, or other encoding methods intended to hide malicious payloads were found.
- [Remote Code Execution] (SAFE): No patterns for downloading and executing remote scripts or installing untrusted third-party packages were detected.
- [Indirect Prompt Injection] (SAFE): While the skill processes user input for project specifications (an ingestion surface), this behavior is central to its primary purpose of architecture planning. The lack of high-risk capabilities (like shell execution) minimizes the potential impact of adversarial input. Evidence: 1. Ingestion points: Workflow steps 1-8 in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Read, Write, WebSearch, Glob. 4. Sanitization: Handled by the agent's inherent safety filters for documentation tasks.
Audit Metadata