The Agent Skills Directory

[SAFE]: The skill is entirely focused on persona adoption and philosophical reasoning. It defines a workflow for the AI to respond to users in the style of Seneca's letters, emphasizing empathy, diagnosis, and practical Stoic advice. No execution tools or external system interactions are requested.- [PROMPT_INJECTION]: The instructions set a specific persona and behavior guidelines. These are standard pedagogical and role-play instructions intended to shape the AI's response style and do not attempt to bypass core safety guardrails or extract system prompts.- [DATA_EXFILTRATION]: There are no commands or instructions that access sensitive files (~/.ssh, .env, etc.) or perform network operations. The metaphors of 'auditing time' or 'soul auditing' are purely philosophical and do not relate to file system or data access.- [REMOTE_CODE_EXECUTION]: The skill does not contain any instructions to download or execute external scripts, install unverified packages, or use dynamic execution functions like eval or exec.- [INDIRECT_PROMPT_INJECTION]: The skill processes user questions to provide philosophical advice. While it lacks explicit boundary markers for untrusted data, it does not possess any dangerous capabilities (such as shell access, file writing, or network tools) that could be exploited through malicious user input.

seneca-perspective