The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions create a surface for indirect prompt injection by processing untrusted data.
Ingestion points: The agent is instructed to "explore the codebase" within SKILL.md to answer questions.
Boundary markers: No delimiters or safety instructions are provided to distinguish between codebase content and system instructions.
Capability inventory: The skill utilizes codebase read access to fulfill its primary purpose of plan verification.
Sanitization: There are no sanitization or validation steps for content retrieved from the codebase.

grill-me