The Agent Skills Directory

[COMMAND_EXECUTION]: The skill implements a command-line wrapper scripts/codeup.py that allows an AI agent to execute complex operations on the Codeup platform, including creating, updating, and deleting files and branches.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. The agent is instructed to read and parse external content such as file contents via get_file and merge request comments via list_merge_request_comments. Maliciously crafted content in these locations could be used to override the agent's instructions.
Ingestion points: File contents retrieved via get_file, and merge request comments retrieved via list_merge_request_comments (documented in SKILL.md).
Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded commands when processing retrieved data.
Capability inventory: The script scripts/codeup.py has high-privilege capabilities including file-write (create_file, update_file), branch management (delete_branch), and organizational data access.
Sanitization: None mentioned in the provided documentation for processing external string data.

codeup