Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed policy-analysis helper that saves optional local planning notes only after user confirmation.
Before installing, know that the skill may save policy preferences, assumptions, drafts, indicators, and scenarios under ~/post-labor-economics/ if you approve. Decline persistence or delete that folder if you do not want future sessions shaped by those saved notes.
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
integration: pending
## System Context
<!-- Geography, institution level, and scope -->
<!-- Time horizon and political constraints -->
## Transition Thesis
The activation criteria are intentionally broad and include common topics like AI jobs, future of work, and automation transition, which creates a real risk of the skill triggering in routine policy or economic discussions without clear user intent. Unintended activation can lead to unnecessary profiling of user preferences and context collection, especially when paired with later instructions to persist integration preferences and planning context.
The skill instructs the agent to persist user preferences in local memory, but the disclosure is incomplete about what data may be retained, how long it will be stored, and the consequences for future interactions. This creates a meaningful privacy and consent risk because users may not understand the breadth of contextual profiling or how saved constraints and preferences could shape later outputs.