The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Bash and Write tools to save generated prompts to the local file system, which involves executing commands based on user-influenced content.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing arbitrary user requests into structured prompts and providing an option for the agent to immediately execute those prompts. This could allow a malicious user to craft a request that, when 'promptified', directs the agent to abuse its tools.
Ingestion points: User-supplied requests processed in the main workflow of SKILL.md.
Boundary markers: None; the skill does not use delimiters to isolate untrusted input.
Capability inventory: The skill has access to Bash, Write, Edit, Grep, Glob, and Agent tools.
Sanitization: No input validation or sanitization is performed on the data being transformed into prompts.

promptify