jira
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALSAFE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process data from Jira (issues, descriptions, and comments) which could contain adversarial instructions.
- Ingestion points: Data is pulled via
jira.issue()andjira.search_issues()inSKILL.md. - Boundary markers: The provided documentation does not include specific boundary markers or instructions for the agent to ignore embedded commands in the issue data.
- Capability inventory: The skill allows the use of
Bash,Read,Write, andEdit, which could be targeted by an injection attack. - Sanitization: No explicit sanitization or validation of Jira field content is shown in the examples.
- [False Positive Alert] (SAFE): The automated scanner flagged
issue.fields.status.nameas a malicious URL. This is a false positive; it is standard Python code using thejiralibrary to access an object attribute and does not represent a network request to a blacklisted domain.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata