multi-presence

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes external data from tools and stores it in YAML state files. This data is later read back into context during synchronization or merging. * Ingestion points: room/activations/*.yml files. * Boundary markers: Absent. * Capability inventory: read_file, write_file, list_dir. * Sanitization: Absent.
  • [External Downloads] (SAFE): No remote resources or package installations are used.
  • [Data Exfiltration] (SAFE): File operations are local; no network-based data transmission detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:34 PM