skills/taxueseek/taxueskills/taxue/Gen Agent Trust Hub

taxue

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local file system path ~/.taxue/growth/patterns.md using the grep utility to inform its internal routing logic, which presents a surface for indirect prompt injection if the file is modified by untrusted sources.
  • Ingestion points: Local file ~/.taxue/growth/patterns.md and user input.
  • Boundary markers: None provided.
  • Capability inventory: Local file reading and multi-skill routing capabilities.
  • Sanitization: No explicit content validation or sanitization of the file content is performed.
  • [SAFE]: The skill manages session state and recovery using local files in the ~/.taxue/ directory, which is a standard and benign practice for persistent state management in complex decision-making workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 07:23 AM