productivity-memory

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is composed exclusively of documentation and instructional Markdown. It does not contain any executable scripts, binary files, or configuration for automated tools.
  • [SAFE]: The memory management architecture involves reading from and writing to local files (CONTEXT.md and memory/) to store user-provided context. It does not perform network operations, access sensitive system credentials, or interact with restricted file paths.
  • [PROMPT_INJECTION]: The skill establishes a data ingestion surface (Indirect Prompt Injection) where the agent is instructed to process internal shorthand and terms from external files to influence its understanding.
  • Ingestion points: Data enters the agent context through CONTEXT.md and the memory/ directory.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the suggested memory structure.
  • Capability inventory: No subprocess calls, file-system execution, or network capabilities are associated with this skill.
  • Sanitization: No validation or sanitization of the content within the memory files is required by the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:08 PM
Security Audit — agent-trust-hub — productivity-memory