analyze-project
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs local analysis of files within the
~/.gemini/antigravity/brain/directory to generate diagnostic reports. This behavior is confined to the local filesystem and aligns with the stated forensic analysis purpose. - [PROMPT_INJECTION]: The skill ingests untrusted data from session artifacts in
~/.gemini/antigravity/brain/(Ingestion Points). No explicit boundary markers or sanitization logic is specified (Sanitization/Boundaries). However, the skill's capabilities are limited to markdown report generation and local artifact updates (Capability Inventory), which does not present a mechanism for code execution or exfiltration.
Audit Metadata