The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill ingests untrusted data from an external source (Jira) which could contain embedded malicious instructions.
Ingestion points: Data enters the agent's context through jira issue view, jira issue list, and jira sprint list commands.
Boundary markers: The instructions lack explicit boundary markers or directions to ignore instructions within the retrieved content.
Capability inventory: The skill allows for various CLI-based operations including issue creation, modification, and deletion via the jira command.
Sanitization: No evidence of sanitization or filtering for the external content before it is processed by the agent.
[External Downloads] (LOW): The skill relies on an external binary jira-cli (hosted at github.com/ankitpokhrel/jira-cli). While this is a widely-used open-source tool, it is not from a predefined trusted organization, and its security depends on the user's installation environment.
[Command Execution] (SAFE): The skill uses subprocess calls to interact with the Jira CLI. The instructions correctly advise using --template files and --no-input flags, which helps mitigate risks associated with shell escaping and interactive prompt injection.

jira-cli