The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a mandatory workflow that ingests data from the user's project codebase, creating a surface for indirect instructions to influence agent behavior.
Ingestion points: The explore-codebase agent in SKILL.md analyzes the project structure and existing patterns, bringing external code into the agent's context.
Boundary markers: Absent; there are no explicit delimiters or instructions to ignore potential malicious prompts embedded within the analyzed files.
Capability inventory: The skill uses the spawn_agent and sniper tools to perform implementation and validation tasks based on the analysis.
Sanitization: Absent; no mechanisms are defined to sanitize or validate the content extracted from the project files.

nextjs-stack