The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read and follow content from multiple external project files, creating an indirect prompt injection surface.
Ingestion points: In SKILL.md, the agent is directed to read RULES.md (line 9), task records (line 11), STATUS.md (line 15), VISUAL-REVIEW.md (line 20), ARTIFACTS.md (line 26), and design.md (line 30).
Boundary markers: The instructions do not specify the use of delimiters or provide warnings to ignore embedded instructions within these external sources.
Capability inventory: The skill manages transitions to other execution skills (like workflow-execute) and is authorized to update task record files based on the reconciled state.
Sanitization: There are no requirements for the agent to sanitize or validate the content of the files before processing them.

resume-task