gpc-enterprise

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the '@gpc-cli/cli' package from the NPM registry and interaction with official Google Cloud APIs (playcustomapp.googleapis.com). These are standard dependencies required for the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill documentation describes a workflow where user-provided inputs, such as app titles and organization names, are interpolated into shell commands (e.g., 'gpc enterprise publish'). This represents a surface for indirect prompt injection or command injection if inputs are not properly sanitized before command generation.
  • Ingestion points: User-supplied parameters for app titles, organization IDs, and organization names (SKILL.md).
  • Boundary markers: Absent; inputs are directly placed within shell command templates.
  • Capability inventory: Shell command execution via the 'gpc' CLI (SKILL.md).
  • Sanitization: Absent; the skill does not provide instructions for escaping or validating these inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 07:46 PM