The Agent Skills Directory

[SAFE]: The skill consists of instructional guidelines and templates for managing project roadmaps via markdown files. It does not contain executable code, external dependencies, or network requests.
[SAFE]: Analysis of the instructions and templates revealed no attempts at prompt injection, obfuscation, or unauthorized data access.
[SAFE]: The skill operates within the project's documentation directory ('docs/tasks/') and does not interact with sensitive system files, environment variables, or credentials.
[SAFE]: The skill ingests data from 'docs/tasks/planning-inbox.md' and 'docs/tasks/backlog.md' as part of its planning workflow. Its capability is limited to writing markdown files back to the 'docs/tasks/' directory. Boundary markers are provided by the markdown templates, and while no explicit sanitization is mentioned, the restricted scope of file-writing operations prevents the execution of malicious payloads, mitigating indirect prompt injection risks.

milestone-planning