roadmap-guide

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): The use of markers like 'CRITICAL' and 'must apply' are contextually appropriate for a style guide and do not attempt to override agent safety or system instructions.
  • [Data Exposure & Exfiltration] (SAFE): No access to sensitive files or network exfiltration patterns were identified.
  • [Remote Code Execution] (SAFE): No external dependencies, remote scripts, or dynamic code execution patterns are present.
  • [Indirect Prompt Injection] (LOW): The skill ingests untrusted data from 'roadmap.md' for formatting purposes. However, it lacks dangerous capabilities (execution or network access) that could be exploited. Mandatory evidence: 1. Ingestion: roadmap.md content; 2. Boundary markers: Absent; 3. Capabilities: None; 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:46 PM