The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information from NOTES.md to define and modify workflow specifications in the workflows/ directory. This creates a surface for indirect prompt injection common to skills that process user data. * Ingestion points: NOTES.md file and interactive user inputs during the grilling session. * Boundary markers: No specific delimiters or safety warnings for external content are defined in the instructions. * Capability inventory: File system access to create, edit, and delete files within the workflows/ directory and NOTES.md file. * Sanitization: No explicit sanitization or validation of the input data is specified.
[SAFE]: No other malicious patterns, such as data exfiltration, remote code execution, or obfuscation, were detected. The skill's operations are confined to the local workspace and match its documented purpose.

loop-me