The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted external data from GitHub issues and pull requests.
Ingestion points: The agent is instructed to use search_issues and read links to issues, PRs, or files to define its task.
Boundary markers: There are no explicit instructions to treat the ingested content as data only or to ignore embedded commands.
Capability inventory: The skill utilizes powerful capabilities including create_pull_request, merge_pull_request, and local shell command execution (bun run).
Sanitization: The skill does not define any sanitization or validation steps for the content retrieved from external links.
[COMMAND_EXECUTION]: The skill executes local shell commands using the bun runtime for testing and building.
Evidence: Specifically mentioned commands include bun run check-types, bun run test, bun run build, and bun run shoot. These are standard tools within the project's development context.

harvest