The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute standard commands such as ls, head, and git (log, status, branch, diff). These operations are used exclusively to gather metadata about the repository state and project files for reporting purposes.
[PROMPT_INJECTION]: The skill processes content from project plan files and session logs to generate summaries. While this represents a potential surface for indirect prompt injection if those files contain untrusted content, it is inherent to the skill's primary function.
Ingestion points: SKILL.md (Phase 1) reads quality_reports/plans/*.md and quality_reports/session_logs/*.md.
Boundary markers: Absent. The skill extracts specific lines directly into the checkpoint structure.
Capability inventory: Includes Read, Write, and Bash access.
Sanitization: Not explicitly mentioned in the instructions.

checkpoint