The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the bun xray CLI tool to perform operations against Xray Cloud and Jira APIs. It facilitates complex test management workflows including test creation, result importing, and project backup/restore operations via shell command execution.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources such as JUnit XML, Cucumber JSON, and Xray JSON files, and modifies local Markdown project documentation. This ingestion of untrusted external content represents a vulnerability surface for indirect prompt injection.
Ingestion points: bun xray import (JUnit/Cucumber/Xray results), bun xray backup restore (JSON backups), and bun xray test enrich (local Markdown PBI cache files).
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded commands in the ingested data.
Capability inventory: The skill possesses the ability to execute CLI commands (bun xray), perform local file writes (test enrich), and perform network operations to Xray and Atlassian services.
Sanitization: No sanitization or validation mechanisms are described for the content of imported files or processed metadata.
[DATA_EXFILTRATION]: The skill manages authentication tokens and API keys by reading from .env and storing them in local configuration files (~/.xray-cli/config.json). Additionally, the bun xray run evidence command provides a mechanism to upload local files to Xray Cloud. While intended for test artifacts, this capability could be used to exfiltrate sensitive local data if the agent is directed to target non-test files.

xray-cli