dx-app-analytics-query
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for retrieving and processing managed package usage data from the ISV Intelligence Data Lake via an external URL.
- Ingestion points: Content of files (CSV or Parquet) downloaded from the presigned
DownloadUrland theErrorMessagediagnostic field defined inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded content are provided for the agent when it processes the downloaded analytics data.
- Capability inventory: The skill uses the
sfCLI (semver >=2.0.0) and REST API calls to interact with sObjects and Metadata API settings. - Sanitization: The instructions do not specify validation or sanitization steps for the data received from the external download link before the agent processes it.
Audit Metadata