jira
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Jira (such as issue descriptions and comments) that could potentially contain instructions designed to influence the agent's logic.
- Ingestion points: Content is retrieved from Jira via
get_issue,search_issues, andget_commentsfunctions inscripts/jira.py. - Boundary markers: The script does not use specific delimiters or instructions to the agent to ignore embedded commands within the fetched Jira data.
- Capability inventory: The skill has the ability to create and modify Jira data (tickets, comments, and workflows) and perform network requests to the configured Jira instance.
- Sanitization: While the script formats data for the Jira API (e.g., Atlassian Document Format), it does not sanitize the content for prompt injection patterns before presenting it to the agent.
Audit Metadata