The Agent Skills Directory

[SAFE]: The skill operates by reading project-specific trackers such as PRD-PIPELINE.md, fix_plan.md, and directory inventories to generate a structured status report. This behavior is consistent with its stated project management purpose.
[PROMPT_INJECTION]: The skill incorporates content from external markdown files into the agent's context without explicit boundary markers. While this creates a surface for indirect prompt injection if those files contain malicious instructions, it is a low-risk architectural pattern inherent to data aggregation tools.
[DATA_EXPOSURE]: The skill reads a local project.conf file to resolve directory names. It does not target sensitive system locations, environment variables, or credential stores.

pmo-status