The Agent Skills Directory

[SAFE]: No malicious patterns, such as prompt injection or obfuscation, were found within the skill instructions. The skill performs legitimate task decomposition and issue creation.
[DATA_EXFILTRATION]: The skill interacts with issue trackers to read and write content. This behavior is documented and matches the intended use case, using standard agent tools within the project context.
[PROMPT_INJECTION]: The skill ingests data from external sources like issue comments and project specs. While this presents a surface for indirect prompt injection, no exploitable high-risk capabilities (like arbitrary code execution or credential exfiltration) are linked to this data flow.

to-issues