aws-cognito-admin
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various administrative
aws cognito-idpCLI commands to manage user pools, users, and app clients. This includes high-impact actions like deleting users and resetting passwords. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from Cognito user attributes.
- Ingestion points: External data enters the agent context via
admin-get-user,list-users, anddescribe-user-poolcommands inSKILL.md. - Boundary markers: Absent. The instructions do not provide delimiters or warnings to the agent to treat user-retrieved data as untrusted or to ignore instructions embedded within those fields.
- Capability inventory: The skill has significant write and delete capabilities, including
admin-delete-user,admin-update-user-attributes, andadmin-reset-user-password(documented inSKILL.md). - Sanitization: Absent. The agent is instructed to display all attributes, including
custom:attributes, and explain their meaning, which requires interpreting potentially malicious content stored in those fields by an attacker.
Audit Metadata