The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @mizzen/cli package from the NPM registry. This package is owned and maintained by the vendor, MizzenAI.
[COMMAND_EXECUTION]: The skill's functionality is built around executing shell commands via the mizzen CLI to manage study guides and interviews.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external interview data. 1. Ingestion points: Untrusted data enters the context through interview transcripts and answers fetched via mizzen conversations transcript and mizzen conversations answers (rules/cli-reference.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflow for handling fetched transcripts. 3. Capability inventory: The skill allows the agent to execute interview management commands, including creating and deleting resources. 4. Sanitization: There is no mention of sanitization or validation of the fetched transcript data before it is presented to the agent.

mizzen-cli