The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted content from GitHub issues, creating a surface for indirect prompt injection. \n * Ingestion points: GitHub issue content is fetched and validated in Step 2 of SKILL.md. \n * Boundary markers: The instructions do not define delimiters or warnings to ignore embedded instructions within the ingested issue body. \n * Capability inventory: The skill executes shell commands (git, gh), writes code to implementation files, and invokes other local sub-agents. \n * Sanitization: There is no mention of filtering or sanitizing external data before it is processed by the agent. \n- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the repository and GitHub API. \n * Evidence: It invokes gh issue edit to assign issues, git push to manage branches, and gh pr create to open draft PRs. These commands are necessary for the skill's primary function and target well-known services.

oh-task