jira-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it automatically ingests data from external and workspace sources without sufficient sanitization or boundary markers.\n
- Ingestion points: The agent is instructed to read configuration from various workspace files, including
.cursor/rules/jira-config.mdc,AGENTS.md, and any generic markdown files. It also retrieves content from Jira issues using thefetchandgetJiraIssueMCP tools.\n - Boundary markers: The instructions do not include explicit delimiters or specific directives for the agent to ignore or isolate instructions that might be embedded within the retrieved Jira issues or workspace documentation.\n
- Capability inventory: The agent is granted capabilities to perform state-changing operations in Jira, such as
createJiraIssue,editJiraIssue,addCommentToJiraIssue, andtransitionJiraIssue.\n - Sanitization: The skill lacks logic to validate or sanitize the data retrieved from external Jira sources before it is processed by the agent or used in subsequent operations.
Audit Metadata