The Agent Skills Directory

[SAFE]: No security issues were identified. The skill is entirely composed of natural language instructions and structural templates for conducting team retrospectives.
[NO_CODE]: There are no scripts, binaries, or external dependencies included in the skill, which eliminates the possibility of code-based attacks or remote code execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided project data (ingestion points in SKILL.md). While it lacks explicit boundary markers or sanitization for this data, it possesses no capabilities such as subprocess calls, file-write, or network operations across any scripts, effectively preventing any potential exploitation.

project-retrospective