The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides the ability to execute various JIRA management tasks through the kdev CLI, including creating, updating, and deleting issues, as well as modifying team membership.
[EXTERNAL_DOWNLOADS]: The skill relies on the installation of an external Node.js package @kmfe/devflow. This package is not from a verified trusted organization or well-known service listed in the analysis framework.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from JIRA tickets.
Ingestion points: Data is ingested through commands such as issue <key> and search <jql> which retrieve summaries, descriptions, and comments from the JIRA system (SKILL.md).
Boundary markers: The instructions do not define boundary markers or provide warnings to the agent to ignore instructions embedded within the JIRA data.
Capability inventory: The agent has Bash access to perform state changes, data deletion (delete), and team management (team-add, team-remove) based on its interpretation of the data (SKILL.md).
Sanitization: There is no evidence of sanitization, filtering, or escaping of the retrieved JIRA content before it is processed by the agent.

devflow-jira