The Agent Skills Directory

[Prompt Injection] (SAFE): No patterns of instruction override, safety filter bypass, or role-play jailbreaks were detected.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or network exfiltration patterns were found.
[Obfuscation] (SAFE): All content is in plain text; no Base64, zero-width characters, or hex-encoded strings were identified.
[Unverifiable Dependencies & RCE] (SAFE): No package managers (pip, npm) or remote script execution (curl | bash) patterns are present. External links point to official documentation domains.
[Indirect Prompt Injection] (LOW): The skill instructs the agent to ingest content from external documentation URLs. This is a standard surface for indirect injection, but the skill lacks any dangerous capabilities (like shell execution or file system writing) that would allow an exploit to manifest.
[Privilege Escalation & Persistence] (SAFE): No commands related to sudo, service installation, or startup script modification were found.

unreal-verse