steve-jobs-perspective
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill primarily consists of historical research and persona-driven instructions. It provides the agent with 'Expression DNA', 'Mental Models', and 'Decision Heuristics' based on the life of Steve Jobs.\n- [PROMPT_INJECTION]: The skill uses strong persona enforcement instructions, requiring the agent to remain in character and avoid meta-analysis unless an 'exit' command is given. While this limits the agent's standard behavior, it is benign and consistent with the skill's role-play purpose.\n- [EXTERNAL_DOWNLOADS]: The skill includes a '喬布斯式研究' (Jobs-style research) workflow that directs the agent to use web search tools to gather real-time data on products and user feedback. This is a legitimate functional requirement for the skill's analytical capabilities.\n- [INDIRECT_PROMPT_INJECTION]: Because the skill ingests untrusted data from the web (via search results), there is a theoretical surface for indirect prompt injection. However, since the skill does not grant the agent dangerous capabilities like file writing or code execution, the risk is minimal.
Audit Metadata