The Agent Skills Directory

[COMMAND_EXECUTION]: The skill references the 'just docs' command in the checklist to verify documentation changes. This utilizes the 'just' command runner, a common tool for task automation in development environments.
[INDIRECT_PROMPT_INJECTION]: The skill involves reading and editing project documentation, which presents a potential surface for indirect prompt injection from untrusted file content. The evidence chain is as follows: (1) Ingestion points: The agent is instructed to read and update files such as README.md, docs/index.yml, and MDX documentation files. (2) Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content within the processed files. (3) Capability inventory: The agent has permissions to edit local files and execute shell commands like 'just docs'. (4) Sanitization: The skill does not specify validation or sanitization routines for the data processed from these files.

contribute-docs