golang-design-patterns
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes a 'Review mode' designed to audit existing Go source code for design issues. This creates a surface for indirect prompt injection where instructions embedded in the audited code could potentially influence the agent's behavior.
- Ingestion points: Auditing existing project code for design patterns and resource leaks (SKILL.md).
- Boundary markers: Absent; there are no specific markers to distinguish between code logic and potentially malicious embedded instructions.
- Capability inventory: The skill has access to powerful tools including
Read,Edit,Write, andBashexecution (SKILL.md). - Sanitization: Absent; there is no explicit instruction to sanitize or ignore non-code content found within the audited files.
Audit Metadata