behavioral-modes
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The skill defines operational modes (personas) like BRAINSTORM and IMPLEMENT. These are legitimate behavioral instructions and do not contain patterns intended to bypass safety filters or ignore system constraints.
- [Data Exposure & Exfiltration] (SAFE): No credentials, sensitive file paths, or exfiltration patterns were detected. Allowed tools (Read, Glob, Grep) are restricted to read-only access.
- [Remote Code Execution] (SAFE): No remote scripts, package installations, or dynamic execution patterns are present.
- [Indirect Prompt Injection] (SAFE): Although the skill defines tools that ingest file data, it lacks the high-risk capabilities (like network-write or code execution) that would make this surface exploitable. All tool usage is restricted to the local environment with read-only permissions.
Audit Metadata