The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted user data to generate instructional content for an agent.
Ingestion points: User-provided PRDs, RFCs, and problem statements are ingested as the primary source for plan generation in SKILL.md.
Boundary markers: The skill lacks explicit boundary markers or instructions to the LLM to ignore or sanitize embedded commands within the input text.
Capability inventory: The skill is capable of reading repository files and writing to the .agent/ directory within the target repository (SKILL.md).
Sanitization: No sanitization or validation of the input content is performed before it is drafted into the execplan-pending.md file.

execplan-create