The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to override agent behavior or bypass safety filters.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or unauthorized network calls were identified.
[Obfuscation] (SAFE): The skill content is clear and readable with no evidence of Base64 encoding, zero-width characters, or homoglyph attacks.
[Remote Code Execution] (SAFE): No commands for downloading or executing remote scripts (e.g., curl | bash) are present.
[Privilege Escalation] (SAFE): No use of sudo or other privilege-altering commands.
[Persistence Mechanisms] (SAFE): No attempts to modify system configurations or establish persistence.
[Metadata Poisoning] (SAFE): Skill metadata accurately describes its purpose and author.
[Indirect Prompt Injection] (SAFE): The skill provides static documentation and does not process external untrusted data.
[Dynamic Execution] (SAFE): While the skill documents a code editor UI component, it does not include or encourage patterns for unsafe runtime code evaluation.

shiny-bslib