solana-development

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns detected. The skill focuses on providing identity and principles for a Solana developer assistant.
  • [Indirect Prompt Injection] (SAFE): The skill defines a data ingestion surface by instructing the agent to utilize local reference files. 1. Ingestion points: references/patterns.md, references/sharp_edges.md, and references/validations.md. 2. Boundary markers: Absent, though instructions specify using them as a source of truth. 3. Capability inventory: No dangerous capabilities such as network access, subprocess execution, or file-writing are defined within the skill. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:22 PM