tiered-memory
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a public GitHub repository for issue tracking and design context.
- Evidence: References to
github.com/bradygaster/squad/issues/1264,686, and600are used to provide status on implementation and design history. - [INDIRECT_PROMPT_INJECTION]: The skill proposes a template that would ingest data from local memory files into an agent's context. While this creates a potential attack surface for indirect prompt injection, it is currently limited to a design proposal with no functional implementation provided in the skill.
- Ingestion points: Data from files in
.squad/memory/are intended to be read in future implementations. - Boundary markers: The design uses Markdown headers and code blocks as delimiters.
- Capability inventory: The skill contains no executable scripts or tools.
- Sanitization: No specific sanitization logic is described in this design document.
Audit Metadata