The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill allows the agent to ingest external, potentially untrusted data from Jira tickets which could contain malicious instructions. \n
Ingestion points: Commands such as jira issue view and jira issue list in references/commands.md pull external summaries and descriptions into the agent's context. \n
Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between its own system prompt and the data retrieved from Jira. \n
Capability inventory: The skill provides significant capabilities to modify Jira state, including creating, editing, and deleting issues, which could be abused if an injection is successful. \n
Sanitization: There is no mention of sanitizing or validating issue content before it is processed by the agent.

jira-cli