The Agent Skills Directory

[PROMPT_INJECTION]: The skill implements a persistent learning mechanism by reading and appending to reference files. Ingestion points: Untrusted data enters the context from learnings.md and user input. Boundary markers: Absent. The skill does not use delimiters to isolate stored learnings from instructions. Capability inventory: File read and append operations on local reference files. No network or shell execution capabilities were detected. Sanitization: Absent. Content is appended to the reference file without validation or escaping.
[NO_CODE]: This skill consists entirely of Markdown instructions and reference documentation; no executable scripts or binary files are included.

sales-checkout