antigravity-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads instructions and context from local project files, which serves as an ingestion point for data that influences agent behavior.
- Ingestion points: The skill reads 'ANTIGRAVITY.md' and project notes as described in SKILL.md.
- Boundary markers: No specific delimiters or safety warnings are used when reading these files.
- Capability inventory: The skill has capabilities for git operations (status, add, commit, push) and file creation (README, .gitignore).
- Sanitization: The skill does not explicitly describe sanitization for the ingested file content.
- [SAFE]: The skill demonstrates positive security practices by instructing the agent to actively check for hardcoded API keys, tokens, and sensitive personal data before performing git operations.
Audit Metadata