xray-cli
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill maintains an attack surface for indirect prompt injection through its data synchronization and enrichment features.
- Ingestion points: External data enters the agent context via Xray Cloud GraphQL and Jira REST API calls during operations such as
test enrich,backup export, andrepair(referenced inSKILL.mdandreferences/backup-restore.md). - Boundary markers: The skill uses a "delimited enrichment section" when writing to local files, but does not provide explicit instructions to ignore potentially malicious embedded instructions within the ingested data.
- Capability inventory: The skill has file-write capabilities (modifying
TEST-*.mdfiles in.context/PBI/and creating JSON backups in.backups/) and network access (communicating with Xray and Jira APIs). - Sanitization: There is no documented evidence of sanitization, filtering, or escaping of external content (such as test summaries or Gherkin definitions) before it is saved to the local environment or interpolated into the agent's context.
Audit Metadata