The Agent Skills Directory

[SAFE]: The skill logic is focused on business sales workflows and does not contain any suspicious code, obfuscated commands, or remote dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted user input.
Ingestion points: SKILL.md accepts arbitrary user input through the {{args}} placeholder.
Boundary markers: No delimiters or protective instructions are used to separate user data from agent instructions.
Capability inventory: The skill environment allows access to Bash, Write, Edit, WebFetch, and Glob tools.
Sanitization: No input validation or sanitization is performed on the arguments passed to the sub-skills.

deal