create-jira-issue
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command (git log) at load time to determine the age of the instructions. While this is used for a policy staleness check, it involves direct shell invocation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from external JIRA issues. This data could potentially contain malicious instructions intended to manipulate the agent's behavior. 1. Ingestion points: JIRA issue summaries, descriptions, and comments retrieved via search and get tools in SKILL.md. 2. Capability inventory: Shell command execution via git, JIRA issue creation, modification, and commenting. 3. Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the retrieved JIRA content. 4. Sanitization: There is no evidence of data validation or sanitization for the content fetched from JIRA.
Audit Metadata