fetching-jira-ticket
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill manages an indirect prompt injection surface by retrieving external data from Jira tickets. It implements specific sanitization to prevent malicious content from being interpreted as instructions. * Ingestion points: Ticket descriptions, comments, and subtask data are retrieved in subagents/ticket-retriever.md. * Boundary markers: The template uses stable headings, and the agent is instructed to rewrite content headers to bold text to avoid collision. * Capability inventory: The skill uses environment-provided Jira read tools and performs local file system writes to the docs/ directory. * Sanitization: Instructions in subagents/ticket-retriever.md and subagents/ticket-retriever-template.md explicitly require rewriting Markdown heading lines as bold labels to ensure they do not collide with the snapshot's reserved headings.
Audit Metadata