jira
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing the atl command-line interface to interact with the Atlassian Jira API.
- [EXTERNAL_DOWNLOADS]: The documentation instructs users to install @ai-foundry/atlassian-bridge globally via npm. This is a community-maintained package and not an official Atlassian tool.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. • Ingestion points: Data is ingested through atl jira issues get and atl jira issues search commands in SKILL.md. • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the retrieved Jira content. • Capability inventory: The agent can create, update, and delete Jira issues via the atl CLI as defined in SKILL.md. • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from Jira issues before it is processed by the agent.
Audit Metadata