The Agent Skills Directory

[SAFE]: No malicious code, obfuscation, or unauthorized data access patterns were detected within the skill instructions.
[CREDENTIALS_UNSAFE]: The skill incorporates a proactive security measure by instructing the agent to identify and redact sensitive information (API keys, passwords, tokens) from user-provided data before including it in the log.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data such as terminal history and logs. Although it does not use specific boundary delimiters for this data, the risk is minimal as the skill's purpose is limited to text formatting and it specifically targets the removal of sensitive information.

dev-log