gke-manifest-generation

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gcloud CLI tool to generate model manifests using arguments provided by the user, such as {model_name} and {output_file_path}. This creates a risk of command injection if the input values are not properly sanitized or escaped before execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates an attack surface where untrusted user input is passed to a command execution tool.
  • Ingestion points: User-provided values for {model_name}, {server_name}, {accelerator_type}, and {output_file_path} in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present for these parameters.
  • Capability inventory: Shell command execution via the gcloud CLI as described in SKILL.md.
  • Sanitization: The instructions do not specify any validation, escaping, or filtering for the user-provided parameters used in the command.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:41 AM
Security Audit — agent-trust-hub — gke-manifest-generation