cubrid-jira
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The instructions include a fallback for the user to install a CLI tool from the vendor's GitHub repository (
github.com/vimkim/cubrid-jira) using theuvtool manager. This is a standard installation procedure for the vendor's own tooling. - [COMMAND_EXECUTION]: The skill uses the
cubrid-jiracommand to search for and update tickets. The commands are structured with specific arguments for ticket IDs and file paths provided by the user or the agent context. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external JIRA issues and local Markdown files, which could theoretically contain instructions intended to influence the agent.
- Ingestion points: Output from
cubrid-jira searchand the content of the--description-file. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: Network access and the ability to modify JIRA issue descriptions via the CLI.
- Sanitization: The skill relies on the CLI tool for data handling and does not specify additional sanitization of the input text.
Audit Metadata