aws-secrets-manager
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from AWS Secrets Manager which could be leveraged for indirect prompt injection if the stored data is compromised. \n
- Ingestion points: The skill uses
aws secretsmanager get-secret-valueinSKILL.mdandreferences/secrets-patterns.md, and theboto3.client('secretsmanager').get_secret_value()method in the Python examples to retrieve secret strings. \n - Boundary markers: There are no explicit instructions or delimiters used to ensure the agent ignores or isolates potential instructions embedded within the retrieved secrets. \n
- Capability inventory: The skill demonstrates capabilities for executing database management commands via
psycopg2, modifying cloud resource policies, and configuring container orchestration via ECS task definitions and Kubernetes manifests. \n - Sanitization: No sanitization or schema validation is performed on the retrieved secret values before they are interpolated into connection strings or executed as part of rotation scripts. \n- [COMMAND_EXECUTION]: The skill provides a large number of AWS CLI commands for interacting with cloud infrastructure, which allows an agent to perform sensitive operations such as creating, deleting, and updating secret resources and their access policies.
Audit Metadata