skill-antigravity
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The instructions are instructional and meta-contextual. No override, bypass, or 'ignore previous instructions' patterns were detected.
- [DATA_EXFILTRATION] (SAFE): No sensitive file paths (~/.ssh, ~/.aws) or network transmission commands (curl, wget) are present.
- [EXTERNAL_DOWNLOADS] (SAFE): Mention of
npx skills addis a reference to an external CLI tool for ecosystem management; the skill itself does not perform or automate these downloads. - [REMOTE_CODE_EXECUTION] (SAFE): No dynamic code execution (eval/exec) or piped remote script executions are present.
- [CREDENTIALS_UNSAFE] (SAFE): No hardcoded API keys, secrets, or private keys found in the skill or metadata.
Audit Metadata