The Agent Skills Directory

[Prompt Injection] (SAFE): No override markers, role-play injections, or instructions to ignore system prompts were found. The text is purely educational.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network operations (curl, wget, etc.) are present.
[Obfuscation] (SAFE): No Base64, zero-width characters, or hidden encoding techniques were detected.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): While the skill mentions crates like thiserror, anyhow, and sqlx, these are provided as documentation examples only. No package installation commands or remote script execution (e.g., curl|bash) are performed.
[Privilege Escalation & Persistence] (SAFE): No commands for sudo, chmod, or system persistence mechanisms (cron, startup scripts) were found.
[Indirect Prompt Injection] (SAFE): The skill does not ingest untrusted external data and lacks capabilities (file writes, network ops) that could be exploited via injection.

rust-patterns