The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run /setup-matt-pocock-skills to scaffold documentation if the project tracker configuration is not found.
[DATA_EXFILTRATION]: The skill's primary function involves extracting information from the user's conversation and codebase to publish it to an external issue tracker.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the conversation and codebase during PRD synthesis. 1. Ingestion points: Conversation context and codebase content referenced in SKILL.md. 2. Boundary markers: No delimiters or warnings are used to prevent the agent from obeying instructions embedded in the ingested content. 3. Capability inventory: File system exploration, issue tracker publishing, and triage label application. 4. Sanitization: No sanitization or validation of the input data is defined before its use in the PRD template.

to-prd