convergent-planning

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains text regarding 'concealing' and 'hiding' (e.g., 'a plan written entirely in confident declaratives is concealing something'), but these terms are used exclusively to describe project management anti-patterns. There is no instruction for the agent to hide its own behavior, ignore safety guidelines, or bypass constraints.
  • [SAFE]: The skill consists entirely of markdown instructions. It does not request any tools, perform network operations, access the file system, or include any third-party dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 03:14 AM
Security Audit — agent-trust-hub — convergent-planning