The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill performs standard software development project setup tasks.
[COMMAND_EXECUTION]: The skill uses shell commands and file writing tools to create directories and index files based on user-provided arguments.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data for context names.
Ingestion points: Untrusted data enters via the $ARGUMENTS variable in SKILL.md.
Boundary markers: None present.
Capability inventory: Uses Bash (mkdir) and Write tools to modify the file system (referenced in SKILL.md).
Sanitization: The skill explicitly instructs the agent to validate that the context name is in kebab-case format and does not already exist, which serves as a safeguard against directory traversal or command injection.

ddd-context