The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown documentation and templates (SKILL.md, references/, assets/). There are no scripts, binaries, or executable files included in the package.
[SAFE]: No malicious patterns such as prompt injection, obfuscation, or credential harvesting were detected. The instructions focus on process improvement and organizational learning.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external data (project details, timelines, and feedback) to generate retrospective reports, it does not utilize any tools that could be abused (e.g., shell access, network requests, or arbitrary file system writes). The risk of exploitation via untrusted input is negligible given the restricted capability scope.

analysis-retrospective