The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified. The skill's primary function is to summarize conversation history for session management.
[DATA_EXFILTRATION]: The skill processes conversation data to create a summary for the user. It does not perform network operations, exfiltrate data to external domains, or access sensitive system configuration files.
[PROMPT_INJECTION]: The skill instructions generate a summary from untrusted conversation history. While this presents an inherent surface for indirect prompt injection, the skill itself contains no malicious overrides or bypass attempts, and its behavior is restricted to session documentation.

claude-handoff