exocortex

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The exo_recall_memories tool retrieves stored data into the agent context, creating a surface for indirect prompt injection if previously stored insights contain adversarial content. Evidence: 1. Ingestion: exo_recall_memories search tool. 2. Boundary markers: None specified in the markdown. 3. Capability inventory: Memory storage, linkage, and retrieval tools. 4. Sanitization: Not described in the skill definition.
  • [External Reference] (LOW): The skill references an external GitHub repository (fuwasegu/exocortex) that is not on the trusted organizations list. This is a documentation link and does not involve automated code execution or package installation.
  • [No Code] (SAFE): The skill consists solely of a markdown definition file without associated scripts or binaries, minimizing the direct execution attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 02:46 PM