agent-platform-prompt-management
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official
google-cloud-aiplatformandgoogle-genailibraries from the standard Python package registry.- [INDIRECT_PROMPT_INJECTION]: The skill manages prompt templates and associated data variables, establishing a surface for indirect prompt injection if malicious content is stored or processed. - Ingestion points: Template strings and user-provided variables processed in
SKILL.mdandreferences/create.md. - Boundary markers: The instructions utilize standard curly brace delimiters (e.g.,
{text}or{{variable}}) to define template placeholders. - Capability inventory: The skill provides access to SDK methods for listing, retrieving, creating, and deleting managed prompt resources.
- Sanitization: The skill relies on the underlying Vertex AI SDK's template interpolation without implementing additional explicit sanitization or filtering logic.- [DYNAMIC_EXECUTION]: The skill generates Python scripts from predefined templates to perform prompt lifecycle operations.
Audit Metadata