The Agent Skills Directory

[SAFE]: No malicious patterns, hidden commands, or unauthorized data access behaviors were detected. The skill performs a legitimate task-management function using established tools and services.
[PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and process information from external sources, such as specification files and remote issue descriptions. While these sources could theoretically contain adversarial instructions, the risk is mitigated by a mandatory human-in-the-loop review step (Step 4) where the user must approve the proposed decomposition before any permanent actions (such as writing to the filesystem or publishing to a tracker) are taken.

to-tickets