ai-interview-article
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured framework for content generation and quality control. It defines a workflow for synthesizing articles from user conversations using specific formatting rules and evaluation criteria (Discovery, External Anchor, 1-sentence test).
- [COMMAND_EXECUTION]: The skill instructs the agent to utilize the 'claude-history' MCP tool (specifically 'conversation_search' and 'recent_chats') to retrieve material from past dialogues. This is a functional requirement for the skill's purpose and does not involve arbitrary command execution or system-level access.
- [DATA_EXPOSURE]: The skill references an external domain 'mued.jp', which is the official website for the author's product ('MUEDnote') mentioned in the skill profile. This link is used for legitimate promotional purposes within the generated articles and does not represent a data exfiltration risk.
- [PROMPT_INJECTION]: Although the skill ingests data from past conversations, which represents an indirect prompt injection surface, the risk is mitigated by the fact that the skill focuses purely on text formatting and quality assessment without requesting dangerous capabilities like file system modifications or external network posts of sensitive data.
Audit Metadata