tigris-lifecycle-management
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the official Tigris CLI package (
@tigrisdata/cli) from the npm registry if it is not detected on the system. - [COMMAND_EXECUTION]: The skill instructions include commands for the
tigrisCLI to interact with bucket lifecycle configurations (set, get, and delete). - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion of external data:
- Ingestion points: Reads lifecycle policies from local JSON files (e.g.,
lifecycle.json) and bucket metadata. - Boundary markers: None explicitly defined in the prompt instructions to separate configuration data from instructional context.
- Capability inventory: The agent can execute CLI commands to modify cloud storage configurations based on these inputs.
- Sanitization: The skill relies on the structured nature of the JSON configuration and the Tigris CLI's own validation mechanisms.
Audit Metadata