The Agent Skills Directory

[SAFE]: The skill does not perform any dangerous operations such as network requests, command execution, or credential harvesting. It is configured with 'disable-model-invocation: true', which restricts its ability to interact with other system tools.
[INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for potentially untrusted data from workspace files.
Ingestion points: The skill reads from 'NOTES.md' to inform its workflow generation.
Boundary markers: There are no instructions to ignore embedded commands in the source files.
Capability inventory: The skill creates and modifies markdown files in the 'workflows/' directory.
Sanitization: No specific sanitization or validation of the input data is described.

loop-me