writer-memory

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely as a local productivity utility with no evidence of malicious patterns or unauthorized data access.- [DATA_EXFILTRATION]: The skill maintains project state and history within a local .writer-memory/ directory. This access is transparently documented and necessary for the core functionality of providing persistent context between sessions.- [PROMPT_INJECTION]: The skill ingests user-provided text for story elements which is subsequently used in agent-generated outputs such as synopses and dialogue validations.\n
  • Ingestion points: Character arcs, attitudes, keywords, and scene notes provided by the user and stored in .writer-memory/memory.json.\n
  • Boundary markers: Absent; user-provided data is interpolated directly into markdown templates.\n
  • Capability inventory: The skill is limited to local file system read/write operations via the fs module in lib/memory-manager.ts.\n
  • Sanitization: None; input is treated as raw text. While this creates a surface for indirect prompt injection, the impact is confined to the quality of the agent's story analysis and does not grant the skill additional capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 12:21 PM