The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language instructions and YAML configuration. It does not include any scripts, binaries, or external library dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from local workspace files, which represents a potential surface for indirect prompt injection if those files contain untrusted or malicious content. However, this interaction is central to the skill's purpose and no dangerous capabilities (like network access or administrative commands) are associated with it.
Ingestion points: The agent reads from NOTES.md and workflows/*.md (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested text.
Capability inventory: The agent is instructed to create, edit, and delete workflow specifications in the workflows/ directory.
Sanitization: No data validation or sanitization steps are specified for the content processed from the workspace files.

loop-me