jira-8-13-17
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents methods to ingest data from an external Jira instance, creating a surface for indirect prompt injection.
- Ingestion points: Data is ingested via multiple operations, such as
getIssue.mdandgetComments.md, which retrieve user-generated content from Jira issues and comments. - Boundary markers: The documentation does not specify delimiters or instructions to treat ingested Jira data as untrusted content.
- Capability inventory: The skill provides significant write and administrative capabilities, including
createIssue.md,addComment.md,changeUserPassword.md, andaddUserToGroup.md. - Sanitization: There are no instructions for the agent to sanitize or validate the content retrieved from Jira before processing it.
Audit Metadata