test-documentation

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Jira tickets (such as acceptance criteria and comments) to facilitate test case generation. This data is pulled into the agent's context through scripts like bun run jira:sync-issues. The skill lacks explicit sanitization or boundary markers for this content, which presents a surface for potential indirect instructions to affect agent behavior.
  • [DYNAMIC_EXECUTION]: The skill uses bun run to perform operational tasks like data synchronization and project hydration using local scripts.
  • [COMMAND_EXECUTION]: The skill makes tool calls to /acli and /xray-cli to perform administrative and documentation tasks in a Jira instance.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:41 PM
Security Audit — agent-trust-hub — test-documentation