qe-aqe-v2-v3-migration

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from legacy project installations to perform migration tasks.
  • Ingestion points: Accesses and reads from existing project directories including .agentic-qe/config.json (configuration), .agentic-qe/memory.db (SQLite database), and .agentic-qe/patterns/ (SKILL.md).
  • Capability inventory: The skill can execute package manager commands (npm install), project CLI tools (aqe migrate), and spawn sub-agents for coding and research tasks (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers are instructed for the data being processed from v2 files.
  • Sanitization: There is no documentation of input validation or sanitization for the legacy memory and configuration data before it is indexed or converted into the v3 format.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:15 PM
Security Audit — agent-trust-hub — qe-aqe-v2-v3-migration