jira-work-links
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Jira issue descriptions, pull request titles, and commit messages, which represents a potential surface for indirect prompt injection. However, the risk is mitigated by explicit instructions requiring the agent to only perform user-authorized actions and verify the resulting link graph. 1. Ingestion points: Jira issue metadata, description fields, and pull request information. 2. Boundary markers: Absent. 3. Capability inventory: Reading and writing Jira issue links, searching source code host repositories. 4. Sanitization: No explicit sanitization of input data is defined.
Audit Metadata