antigravity-skill-orchestrator

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a master skill catalog from the author's GitHub repository (sickn33/antigravity-awesome-skills) to identify additional capabilities when local tools are insufficient.
  • [PROMPT_INJECTION]: The skill maintains an indirect prompt injection surface due to its core function of processing external data to guide agent behavior.
  • Ingestion points: Retrieves workflow data from the @agent-memory-mcp tool and skill definitions from a remote GitHub-hosted catalog.
  • Boundary markers: No explicit delimiters or instructions are used to isolate or ignore instructions potentially embedded within the retrieved catalog or memory data.
  • Capability inventory: Performs network operations to fetch the catalog and utilizes tools for persistent memory storage and retrieval.
  • Sanitization: Data from the external catalog and user-populated memory is not sanitized or validated before being integrated into the agent's task execution context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 03:37 AM