swanlab-skill
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute the
swanlabCLI to interact with the SwanLab platform. It includes commands for workspace information, project creation, and metric retrieval. Notably, some self-hosted management commands accept passwords as command-line arguments, which is a common but less secure practice compared to environment variables. - [PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by fetching and processing external data.
- Ingestion points: The skill ingests untrusted data via
swanlab api run logs,swanlab api project info, andswanlab api run info, which retrieve user-supplied logs, project descriptions, and metadata from the platform. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat this external data as untrusted or to ignore instructions embedded within it.
- Capability inventory: The agent has the capability to execute shell commands via the
swanlabCLI. - Sanitization: There is no evidence of sanitization or filtering of the fetched data before it is presented to the agent context.
Audit Metadata