The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is entirely instructional and serves as a role definition for an AI assistant to provide GCP-related advice. It explicitly recommends against insecure practices like hardcoding credentials.- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes user input within its core instructions.
Ingestion points: Untrusted data is ingested through the $ARGUMENTS variable in the main skill definition.
Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore commands embedded within the user-provided arguments.
Capability inventory: The skill is a 'no-code' skill with no executable scripts, file system access, or network capabilities.
Sanitization: No input validation or escaping is applied to the $ARGUMENTS variable.

gcp-expert