execution-roadmaps
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions focus exclusively on project planning workflows and do not contain any patterns attempting to override agent behavior or bypass safety constraints.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, credentials, or network operations are present. Operations are limited to local artifact generation in the
./artifacts/directory. - [Remote Code Execution] (SAFE): There are no external dependencies, remote scripts, or dynamic code execution patterns. The skill consists entirely of Markdown instructions and templates.
- [Indirect Prompt Injection] (LOW): The skill ingests user input to generate roadmaps. While this creates a surface for indirect injection, the risk is mitigated by the restricted toolset (basic file operations) and the lack of network or system-level capabilities.
- [Persistence Mechanisms] (SAFE): No attempts to modify system configurations, shell profiles, or scheduled tasks were detected.
Audit Metadata