The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were detected in the markdown files.
[Data Exposure & Exfiltration] (SAFE): No sensitive file access (e.g., .ssh, .aws) or hardcoded credentials were identified. The skill does not perform any network operations.
[Obfuscation] (SAFE): Content is presented in clear markdown; no Base64, zero-width characters, or hex encoding was found.
[Unverifiable Dependencies] (SAFE): No package managers (npm, pip) or remote code execution patterns (curl|bash) are used.
[Indirect Prompt Injection] (SAFE): The skill lacks data ingestion points and tool capabilities (subprocess calls, file-write), meaning it has no attack surface for indirect injection.
[Dynamic Execution] (SAFE): No runtime compilation or dynamic code generation logic is present in the provided files.

code-architect