memory-summarization
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process conversation history, which is untrusted data that may contain malicious instructions.
- Ingestion points: Conversation messages are ingested for rolling, hierarchical, and token-aware summarization (SKILL.md).
- Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions to separate conversation data from processing logic.
- Capability inventory: The skill is configured with powerful tool access, including
Bash,Write, andEdit(SKILL.md). - Sanitization: There are no documented methods for sanitizing or escaping the conversation content before it is interpolated into LLM prompts or processed by system tools.
Audit Metadata