use-jira-cli
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the
jiraCLI tool to manage project tasks. It appropriately mandates the use of non-interactive flags such as--plain,--raw, and--no-inputto ensure the agent does not hang waiting for user input. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests untrusted data from an external source.
- Ingestion points: Data from Jira issues, including summaries, descriptions, and comments, is pulled into the agent's context via commands like
jira issue viewandjira issue list. - Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore or isolate instructions found within the retrieved Jira data.
- Capability inventory: The agent has the capability to perform write operations in Jira (creating issues, editing content, adding comments, and transitioning statuses) based on the processed data.
- Sanitization: No sanitization or validation steps are defined to filter malicious payloads or instructions embedded in the issue metadata or body.
Audit Metadata