The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project planning files which serves as a potential vector for instructions to influence agent behavior, especially given its broad tool access.
Ingestion points: Reads project-specific data from .planning/STATE.md and .planning/ROADMAP.md (SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic described in SKILL.md.
Capability inventory: The skill is granted access to Bash, Write, Skill (dispatching), and Agent (background task creation) tools.
Sanitization: The skill instructions do not specify any validation or sanitization routines for the content ingested from the project files.

gsd-manager