pscale-org
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various administrative commands using the
pscaleCLI. These include operations to switch organizations (pscale org switch), manage members (pscale org member update/remove), and configure authentication settings (pscale org sso configure/enable). - [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes external, potentially untrusted data that is then interpolated into shell commands.
- Ingestion points: Untrusted data enters the agent context through placeholders such as
<org-name>,<email-or-user-id>,<team-id>,<name>, and<description>used inSKILL.mdworkflows. - Boundary markers: There are no explicit boundary markers or delimiters defined to separate user-provided data from the command structure in the instructions.
- Capability inventory: The skill has the capability to execute shell commands via the
pscaleCLI, which can modify organization settings, remove members, and change access controls. - Sanitization: The skill instructions do not specify any sanitization, escaping, or validation logic for the external content before it is passed to the CLI.
Audit Metadata