memory-updater
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (INFO): The skill is purely instructional and does not contain any executable scripts, binaries, or tool specifications.
- [SAFE] (INFO): No evidence of prompt injection, data exfiltration, or obfuscation was found in the provided content.
- [Category 8: Indirect Prompt Injection] (LOW): While the skill involves persisting session data to files, which can be an attack surface for indirect prompt injection, it is a standard workflow for context management. 1. Ingestion points: Current session context. 2. Boundary markers: Not specified. 3. Capability inventory: File-writing via agent's core tools. 4. Sanitization: Not specified.
Audit Metadata