The Agent Skills Directory

No Executable Content (SAFE): The skill consists entirely of markdown documentation and does not include any scripts, binaries, or automated command executions.
Primary Purpose Alignment (SAFE): The data fetching and categorization instructions are strictly aligned with the intended accounting use case, with no evidence of unauthorized data access.
Standard Data Surface (SAFE): While the skill processes external transaction memos—a common surface for indirect prompt injection—this activity is inherent to its primary financial reporting function and is considered safe within the agent's operational context.

roll-forward