jira-bug
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which could lead to instructions embedded in those sources influencing agent behavior.
- Ingestion points: The skill fetches Jira issue summaries, descriptions, and comments (Workflow Step 1) and reads Git diffs and source code (Workflow Step 3).
- Boundary markers: The workflow instructions do not specify the use of delimiters (like triple backticks or XML tags) or explicit instructions for the model to ignore potential commands embedded within the ticket content or code comments.
- Capability inventory: The skill uses tools for Jira site discovery, issue retrieval, comment listing, comment creation, and local Git operations (git diff, git status).
- Sanitization: There are no documented steps for sanitizing, escaping, or filtering external content before it is processed by the AI or published as a new Jira comment.
Audit Metadata