gemini-skill-creator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): No instructions were found that attempt to bypass agent safety filters or override system instructions.
- [DATA_EXFILTRATION] (SAFE): No file system access to sensitive directories or network communication to non-whitelisted domains was identified.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill does not download or execute remote scripts or external packages.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill defines how to structure new skills based on user input, it does not implement any active data ingestion or processing logic that would facilitate an injection attack within its own context.
Audit Metadata