The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute git diff and git log to extract repository changes for analysis. It also references a project-specific setup command /setup-matt-pocock-skills to be used if required configuration files are missing.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It ingests untrusted data from repository files (such as specifications, PRDs, and style guides) and git diffs, then interpolates this content into the prompts of "general-purpose" sub-agents.
Ingestion points: Data enters the context via git diff output and various local files in docs/, specs/, .scratch/, and standard files like CLAUDE.md or .editorconfig.
Boundary markers: There are no explicit boundary markers or instructions to the sub-agents to ignore potentially malicious instructions embedded within the analyzed content.
Capability inventory: The skill utilizes the Agent tool to spawn sub-agents which process the ingested data.
Sanitization: No sanitization or validation of the external content is performed before passing it to the sub-agents.

review