memory
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a standard durable memory mechanism using local Markdown files to persist context and preferences across agent sessions.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by storing interaction data that is subsequently re-read into the agent context. • Ingestion points: Data is read from .opc/memory/global.md and project-specific Markdown files as defined in SKILL.md. • Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions to isolate the stored data from active instructions. • Capability inventory: The skill is limited to file system read and write operations and does not involve network access or shell command execution. • Sanitization: The instructions do not define sanitization or validation logic for the content being persisted to the memory files.
Audit Metadata