The Agent Skills Directory

[COMMAND_EXECUTION] (INFO): Employs bb (Babashka) and just for executing local functional programming logic. These are standard task runners and scripting environments.
[DATA_EXFILTRATION] (SAFE): No evidence of network operations or access to sensitive local files (e.g., credentials, SSH keys).
[REMOTE_CODE_EXECUTION] (SAFE): Does not download or execute remote scripts. All logic is contained within the provided skill file.
[OBFUSCATION] (SAFE): Uses esoteric mathematical and category theory terminology (GF(3), Ergodic, Triads), but this is consistent with its stated purpose and does not serve to hide malicious intent.
[PROMPT_INJECTION] (SAFE): No instructions targeting agent behavior modification or safety filter bypasses.

cat