The Agent Skills Directory

[SAFE]: No security issues were detected. The skill follows a well-defined instructional path for architectural analysis and documentation updates.
[DATA_EXFILTRATION]: The skill reads from and writes to project-specific memory files such as memory/SPEC.md and memory/PLAN.md. This behavior is consistent with the skill's purpose and does not involve unauthorized network transmission or data exposure.
[PROMPT_INJECTION]: The skill uses user arguments and project files as context. Analysis shows no attempts to override agent behavior or bypass safety filters within these instructions.

ln-oracles