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
Risk Level
SAFE
Analyzed
Sep 7, 2026, 01:40 PM
Security Audit — agent-trust-hub — antigravity-workflow