capture
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes conversation history which could contain untrusted user input.
- Ingestion points: The skill reads the conversation history to generate summaries (SKILL.md).
- Boundary markers: No explicit delimiters are specified for the summarized content.
- Capability inventory: The skill performs file writes to the
.maestro/directory (SKILL.md). - Sanitization: No explicit sanitization or filtering of historical content is mentioned.
- Assessment: This is an inherent property of summarization tools; the risk is low as it follows the primary intended purpose of session management.
Audit Metadata