jira
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute
which uvfor environment verification andcubrid-jira-searchto fetch ticket data based on user input (TICKET_ID). - [EXTERNAL_DOWNLOADS]: References the
uvtool from a well-known service (Astral) and suggests the installation of thecubrid-jira-fetcherpackage if the utility is not found. - [PROMPT_INJECTION]: Vulnerability surface for indirect prompt injection identified.
- Ingestion points: Remote data fetched from the JIRA REST API via the
cubrid-jira-searchutility (specified in SKILL.md). - Boundary markers: Absent; the skill instructs the agent to present output to the user "as-is".
- Capability inventory: Shell command execution via the Bash tool (which, cubrid-jira-search) in SKILL.md.
- Sanitization: Absent; no validation or escaping is performed on the retrieved JIRA content before it is processed by the agent.
Audit Metadata