The Agent Skills Directory

[SAFE]: The skill exclusively utilizes proprietary tools prefixed with iskron_ (e.g., iskron_case, iskron_add_*, iskron_orient), which are vendor-specific resources for the Iskron platform.
[SAFE]: No attempts to access sensitive local system files (e.g., SSH keys, environment variables) or execute unauthorized shell commands were found.
[SAFE]: Analysis of the instructions and metadata revealed no evidence of prompt injection, obfuscation, or persistence mechanisms.
[INDIRECT_PROMPT_INJECTION]: The skill operates on data from shared cases and graph nodes, which presents a surface for indirect prompt injection. However, the instructions mandate strict adherence to structured operational protocols ("Сквозные нормы") and verification steps (e.g., "Принимай прогоном проверки"), which serve as significant mitigations against accidental or malicious instruction execution from data.

architect