tigris-object-operations
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install the official @tigrisdata/cli package from the NPM registry to enable storage management.
- [COMMAND_EXECUTION]: Shell commands are used to verify the presence of the Tigris CLI and install it globally if necessary (tigris help || npm install -g @tigrisdata/cli). Further operations are performed using the library and CLI tool.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve data from external storage buckets, which introduces a potential surface for indirect prompt injection if the stored content contains malicious instructions.
- Ingestion points: Data is ingested via the get() function in SKILL.md (supporting string, file, or stream formats).
- Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within the downloaded data are provided.
- Capability inventory: The skill possesses capabilities for writing to storage (put), deleting objects (remove), and executing CLI commands.
- Sanitization: The instructions do not define sanitization or validation steps for the fetched data.
Audit Metadata