The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the conversation history and project codebase to generate a Product Requirements Document (PRD), which is then published to an external issue tracker.
Ingestion points: Processes the current conversation context and the project's codebase content (SKILL.md).
Boundary markers: No specific delimiters or instructions are used to distinguish between system instructions and untrusted data from the codebase or conversation.
Capability inventory: The skill possesses the ability to read the entire codebase and write/publish content to a project issue tracker.
Sanitization: No evidence of sanitization, escaping, or validation of the ingested codebase or conversation content before it is processed or published.
[COMMAND_EXECUTION]: The instructions direct the agent to execute a setup command (/setup-matt-pocock-skills) to initialize the environment with issue tracker vocabulary if not already present. This represents a dependency on an external command for configuration.

to-prd