consolidate-memory
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes memory files which may contain untrusted data from project sources or external contributions, creating a surface for indirect prompt injection.
- Ingestion points: Reads project-level
MEMORY.mdand.claude/state/personal-memory.mdfiles. - Boundary markers: The skill does not implement specific delimiters to isolate external content from its own instructions during the 'Dream' (Abstraction) phase.
- Capability inventory: The skill has the ability to write and edit files on the local filesystem.
- Sanitization: Content is consolidated and rewritten without explicit sanitization, however, the skill mandates a manual confirmation step where the full proposed output must be approved by the user before any write operation is performed.
Audit Metadata