awsflow-dynamodb
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from DynamoDB tables, which may contain untrusted content from external sources, creating a surface for indirect prompt injection.
- Ingestion points: The skill retrieves data through the
Scan,Query, andGetItemcommands defined inSKILL.md. - Boundary markers: Absent. The instructions do not specify the use of delimiters or provide warnings to the agent to ignore any embedded instructions within the retrieved database content.
- Capability inventory: The skill provides access to high-impact capabilities including
DeleteTable,DeleteItem,PutItem,UpdateItem, andRestoreTableFromBackup. - Sanitization: Absent. No instructions are provided for the agent to validate, filter, or escape the content fetched from the database before it is incorporated into the prompt context.
- [COMMAND_EXECUTION]: The skill enables the execution of administrative commands targeting AWS infrastructure through the
DynamoDBTool. - Evidence: The commands
DeleteTable,UpdateTable,DeleteBackup, andRestoreTableFromBackupinSKILL.mdgrant the agent the ability to perform architectural and destructive changes to the DynamoDB environment.
Audit Metadata