The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read task descriptions and comments using nitro agent tasks show and search subcommands. Because these fields can contain arbitrary text, they represent a surface for indirect prompt injection where malicious instructions could be embedded by other users or previous agent sessions.
Ingestion points: Task descriptions and comment logs retrieved via the Nitro CLI (SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing task content.
Capability inventory: The agent uses shell commands to interact with the nitro CLI for creating, updating, and querying tasks.
Sanitization: No explicit sanitization or validation of the task content is described before the agent processes it.
[EXTERNAL_DOWNLOADS]: The skill references documentation at https://chillicream.com/docs/nitro/cli/installation for manual CLI installation by the user. This is a vendor-owned resource for the Nitro tool.

nitro-task