tigris-iam

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of the 'tigris' CLI to perform administrative tasks such as creating, editing, and deleting IAM policies, as well as managing organization users and roles. These operations are conducted through subcommands like 'tigris iam policies create' and 'tigris iam users invite', which are standard functional requirements for IAM management within the Tigris platform.
  • [SAFE]: The skill exhibits an attack surface for indirect prompt injection due to its handling of external JSON policy documents. * Ingestion points: The skill reads policy documents from local files or stdin using the '--document' flag in policy creation and edit commands. * Boundary markers: No explicit delimiters or instructions to ignore instructions embedded within the JSON documents are provided in the documentation. * Capability inventory: The 'tigris' CLI subcommands allow for organization-level permission changes, user invitations, and access revocation. * Sanitization: The documentation does not specify sanitization or validation logic for the input documents prior to processing by the CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 07:42 PM