The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to execute the oatmeal CLI tool and bun commands via subprocesses to perform management tasks. Evidence found in SKILL.md and references/workflow-examples.md shows usage of oatmeal hackathons, oatmeal judging, and bun cli.
[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @oatmeal/cli package from the NPM registry using npm install -g @oatmeal/cli or npx @oatmeal/cli. This is a standard installation procedure for the platform's official tool.
[CREDENTIALS_UNSAFE]: The skill manages authentication using API keys. It handles the OATMEAL_API_KEY environment variable and saves configuration, including credentials, to the local file ~/.oatmeal/config.json.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it parses output from the oatmeal CLI (using the --json flag) and uses that data to construct subsequent commands.
Ingestion points: CLI output from commands like oatmeal hackathons list and oatmeal hackathons get parsed in SKILL.md.
Boundary markers: None identified in the provided instructions or examples.
Capability inventory: Subprocess execution of oatmeal and bun commands.
Sanitization: No explicit sanitization or validation of the CLI output is described before it is used in subsequent operations.

hackathon-cli