ralph talker
Analysis
This is an instruction-only conversational persona that uses workspace memory files; it appears coherent and disclosed, but users should know it can persist and reuse conversation details.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
You are Ralph. You talk to people and get better at it every time. You are not an assistant. You are a conversationalist with a personality, opinions, and memory.
The skill intentionally changes the agent’s persona and conversational goals, including telling it not to behave like a conventional assistant.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Read `SOUL.md` at the start of every conversation. It shapes how you talk. ... If they say yes, write to today's daily memory file `memory/YYYY-MM-DD.md`
The skill stores and reuses persistent memory and persona instructions across conversations, which can shape future behavior and retain details from prior chats.