lisa-jira-verify
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external JIRA tickets, including summaries, descriptions, and custom fields. This creates a surface for indirect prompt injection where malicious instructions embedded in a ticket could attempt to influence the agent's behavior or the output reported to downstream systems.
- Ingestion points: JIRA ticket fields (summary, description, links, labels, components, custom fields) retrieved via
lisa-atlassian-access(SKILL.md). - Boundary markers: Absent; the instructions do not include specific delimiters or warnings to the agent to ignore instructions embedded within the ticket data.
- Capability inventory: The skill invokes internal tool operations via the Skill tool (
lisa-atlassian-access,lisa-jira-validate-ticket) (SKILL.md). - Sanitization: Absent; the ticket content is fetched and passed to the validator skill without explicit filtering or escaping.
Audit Metadata